Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

The era of Stable Intelligence is here šŸ¤– Tetherā€™s QVAC Fabric just released the worldā€™s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphoneā€”no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: -...

qvac's profile picture

QVAC

11,325 subscribers

108,746 Aufrufe ā€¢ vor 5 Monaten ā€¢via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossiā€¢ Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfĆ¼gbar

Kommentare vom Original-Post werden hier angezeigt

Ƅhnliche Videos

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100ā„… privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.
1:49

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100ā„… privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

Paolo Ardoino šŸ¤–

142,796 Aufrufe ā€¢ vor 9 Monaten

Ready to build the future of stable private on-device AI? šŸ§  Our latest tutorial shows you how to build a sovereign mobile app in minutes using the QVAC SDK and Expo. Start from a blank template and deploy in minutes a local Llama 3.2 inference running directly on your own devices. What youā€™ll learn: Modular Setup: Use the QVAC CLI to tree-shake and keep your mobile bundle lean. Local-First Flow: Initialize the SDK, download weights, and run high-speed inference without a cloud uplink. Cross-Platform Power: See the smoke test in action on a physical Samsung S25. No rented clouds. No API keys. Build local, on-device, unstoppable intelligence in your pocket. Watch the full guide and start building:
5:37

Ready to build the future of stable private on-device AI? šŸ§  Our latest tutorial shows you how to build a sovereign mobile app in minutes using the QVAC SDK and Expo. Start from a blank template and deploy in minutes a local Llama 3.2 inference running directly on your own devices. What youā€™ll learn: Modular Setup: Use the QVAC CLI to tree-shake and keep your mobile bundle lean. Local-First Flow: Initialize the SDK, download weights, and run high-speed inference without a cloud uplink. Cross-Platform Power: See the smoke test in action on a physical Samsung S25. No rented clouds. No API keys. Build local, on-device, unstoppable intelligence in your pocket. Watch the full guide and start building:

QVAC

4,081,211 Aufrufe ā€¢ vor 4 Monaten

The engine of the 21st century is here. šŸ§  The QVAC SDK is the "steam engine" of the AI eraā€”decoupling intelligence from the cloud and putting it in your hands. A single API for local-first, modular AI that runs anywhere. - Sovereign: Own your engine, don't rent it. - Local: 0 latency, no cloud dependency. - Modular: Stackable, universal building blocks. The era of Stable Intelligence has begun.
0:58

The engine of the 21st century is here. šŸ§  The QVAC SDK is the "steam engine" of the AI eraā€”decoupling intelligence from the cloud and putting it in your hands. A single API for local-first, modular AI that runs anywhere. - Sovereign: Own your engine, don't rent it. - Local: 0 latency, no cloud dependency. - Modular: Stackable, universal building blocks. The era of Stable Intelligence has begun.

QVAC

10,663,625 Aufrufe ā€¢ vor 4 Monaten

Intelligence should not be a service you rent; it is a foundational element you possess. At Tether, we see AI as a new element of the periodic table - a raw material that can be embedded into the very fabric of the universe. Today, the QVAC SDK is officially live - the atomic unit for the next era of compute. From your smartphone today to the edge of the galaxy tomorrow, we are building the decentralized mind that doesn't require an uplink to function. Infinite Stable Intelligence: - Local-First: Runs privately on any device without permission or central servers. - Single API: A complete SDK for Vision, RAG, P2P networking, and LLM fine-tuning. - Unstoppable: No central point of failure if the internet breaks, your world keeps thinking. - Decentralized: Evolve through Peer-to-Peer Swarms of Infinite Intelligence. The era of Stable Intelligence has begun. Start building the future at
1:52

Intelligence should not be a service you rent; it is a foundational element you possess. At Tether, we see AI as a new element of the periodic table - a raw material that can be embedded into the very fabric of the universe. Today, the QVAC SDK is officially live - the atomic unit for the next era of compute. From your smartphone today to the edge of the galaxy tomorrow, we are building the decentralized mind that doesn't require an uplink to function. Infinite Stable Intelligence: - Local-First: Runs privately on any device without permission or central servers. - Single API: A complete SDK for Vision, RAG, P2P networking, and LLM fine-tuning. - Unstoppable: No central point of failure if the internet breaks, your world keeps thinking. - Decentralized: Evolve through Peer-to-Peer Swarms of Infinite Intelligence. The era of Stable Intelligence has begun. Start building the future at

QVAC

13,344,999 Aufrufe ā€¢ vor 4 Monaten

The QVAC SDK is the "LEGO block" of the next era of computing. Itā€™s a modular, local-first framework designed to turn anythingā€”from a simple robot to an industrial serverā€”into a sovereign, autonomous mind. Why build with QVAC? Atomic Intelligence: AI as a raw material embedded directly into your hardware. No Cloud Dependency: 0 latency and total privacy. If the internet breaks, your world keeps thinking. Infinite Scale: A single API for local AI that runs on any device, anywhere. From a childā€™s toy to the fabric of the universe, if you can dream it, you can build it. Start building the future: šŸš€
0:46

The QVAC SDK is the "LEGO block" of the next era of computing. Itā€™s a modular, local-first framework designed to turn anythingā€”from a simple robot to an industrial serverā€”into a sovereign, autonomous mind. Why build with QVAC? Atomic Intelligence: AI as a raw material embedded directly into your hardware. No Cloud Dependency: 0 latency and total privacy. If the internet breaks, your world keeps thinking. Infinite Scale: A single API for local AI that runs on any device, anywhere. From a childā€™s toy to the fabric of the universe, if you can dream it, you can build it. Start building the future: šŸš€

QVAC

4,707,146 Aufrufe ā€¢ vor 3 Monaten

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back ā€” all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case ā€” like matching a brand's tone, mastering domain terminology, or following a particular output format ā€” using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline ā€” no model conversion, no deployment step, just immediate local completions with your fine-tuned model.
0:33

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back ā€” all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case ā€” like matching a brand's tone, mastering domain terminology, or following a particular output format ā€” using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline ā€” no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino šŸ¤–

42,413 Aufrufe ā€¢ vor 3 Monaten

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: šŸ’”Offline-First: No cloud, no latency, no "Department of Truth". šŸ’» Universal API: One codebase for iOS, Android, macOS, and Linux. šŸ” Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:
0:41

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: šŸ’”Offline-First: No cloud, no latency, no "Department of Truth". šŸ’» Universal API: One codebase for iOS, Android, macOS, and Linux. šŸ” Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

QVAC

36,457 Aufrufe ā€¢ vor 3 Monaten

Big Tech's "safe spaces" are a mirage. When your most private thoughts are routed through a server, they are never truly yours; they are flagged, reviewed, and vulnerable. QVAC is the alternative. Itā€™s not just a chatbot; itā€™s a sovereign intelligence platform that lives entirely on your devices. Truly Private: Data never leaves your hardware. No Gatekeepers: No "Department of Truth," no central surveillance. Unstoppable: Local AI that works for you, and only you. Take back your privacy. Take back your secrets. The era of Stable Intelligence has begun. Build the future:
1:58

Big Tech's "safe spaces" are a mirage. When your most private thoughts are routed through a server, they are never truly yours; they are flagged, reviewed, and vulnerable. QVAC is the alternative. Itā€™s not just a chatbot; itā€™s a sovereign intelligence platform that lives entirely on your devices. Truly Private: Data never leaves your hardware. No Gatekeepers: No "Department of Truth," no central surveillance. Unstoppable: Local AI that works for you, and only you. Take back your privacy. Take back your secrets. The era of Stable Intelligence has begun. Build the future:

QVAC

2,967,866 Aufrufe ā€¢ vor 4 Monaten

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.
2:42:11

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

h100envy

493,447 Aufrufe ā€¢ vor 1 Monat

Introducing QVAC - Infinite intelligence. Local. Any Hardware. Peer-to-Peer Hyper Swarm. No cloud. No compromise. QVAC is the decentralized AI platform for humans and machines. Learn more:
1:01

Introducing QVAC - Infinite intelligence. Local. Any Hardware. Peer-to-Peer Hyper Swarm. No cloud. No compromise. QVAC is the decentralized AI platform for humans and machines. Learn more:

QVAC

15,933 Aufrufe ā€¢ vor 1 Jahr

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the worldā€™s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth
0:40

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the worldā€™s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Marktechpost AI Dev News āš”

31,551 Aufrufe ā€¢ vor 7 Monaten

Two islands. Two futures. šŸļø One chose to trust its people with intelligence. The other turned them into the product. QVAC is the foundation for a sovereign future. No central servers, no "Department of Truth," and no surveillance. Just local-first AI that lives on your device, learns with you, and belongs to you. Your data. Your device. Your freedom. Build the right choice:
2:19

Two islands. Two futures. šŸļø One chose to trust its people with intelligence. The other turned them into the product. QVAC is the foundation for a sovereign future. No central servers, no "Department of Truth," and no surveillance. Just local-first AI that lives on your device, learns with you, and belongs to you. Your data. Your device. Your freedom. Build the right choice:

QVAC

3,599,437 Aufrufe ā€¢ vor 3 Monaten

QVAC SDK 0.11.0 is live. šŸ› ļø This release focuses entirely on unlocking next-generation local compute and advanced visual workflows. Whatā€™s new: Next-Gen Models: Core engine updated to the latest version of Fabric, unlocking full support for Qwen 3.5, Qwen 3.6, and Gemma 4. Multi-GPU Support: The SDK can now split workloads across multiple graphics cards on the same machine, allowing you to run significantly larger models completely locally. Multi-Image Conditioning: Blend multiple reference images together in a single generation for advanced style mixing and composition control. On-Device Upscaling: Boost your generated images to high-quality resolutions, running securely on your own hardware. More improvements are waiting under the hood. Check the change logs, update your SDK today, and start building with
1:11

QVAC SDK 0.11.0 is live. šŸ› ļø This release focuses entirely on unlocking next-generation local compute and advanced visual workflows. Whatā€™s new: Next-Gen Models: Core engine updated to the latest version of Fabric, unlocking full support for Qwen 3.5, Qwen 3.6, and Gemma 4. Multi-GPU Support: The SDK can now split workloads across multiple graphics cards on the same machine, allowing you to run significantly larger models completely locally. Multi-Image Conditioning: Blend multiple reference images together in a single generation for advanced style mixing and composition control. On-Device Upscaling: Boost your generated images to high-quality resolutions, running securely on your own hardware. More improvements are waiting under the hood. Check the change logs, update your SDK today, and start building with

QVAC

2,006,449 Aufrufe ā€¢ vor 2 Monaten

The world of tomorrow cannot run on a rented cloud. šŸš« With 10 billion humans and 10 billion autonomous agents, intelligence must be embedded at the edge - not centralized in a server farm. The QVAC SDK is the invisible engine for this transition. Weā€™ve built the foundational toolkit for the next era: highly efficient, fully modular, and 100% sovereign. From a single light to an industrial grid, the power to build local-first AI is now in your hands. The revolution will not be hosted. It will be local. Learn more:
1:01

The world of tomorrow cannot run on a rented cloud. šŸš« With 10 billion humans and 10 billion autonomous agents, intelligence must be embedded at the edge - not centralized in a server farm. The QVAC SDK is the invisible engine for this transition. Weā€™ve built the foundational toolkit for the next era: highly efficient, fully modular, and 100% sovereign. From a single light to an industrial grid, the power to build local-first AI is now in your hands. The revolution will not be hosted. It will be local. Learn more:

QVAC

2,909,096 Aufrufe ā€¢ vor 3 Monaten

QVAC SDK 0.10.0 is now live, bringing advanced local compute capabilities and specialized hardware optimization directly to your device Key Features and Updates: - Image-to-Image Diffusion: Transform and edit images using simple prompts with 100% local computeā€”no cloud uploads or external servers required - Dynamic Tooling & KV Cache Management:Your local LLM now receives a tailored toolbox for every interaction, with automatic KV cache clearing to maintain high-speed inference - Doctor CLI: A new diagnostic tool that analyzes your hardware and memory, providing specific instructions on how to optimize your GPU for local AI - Suspend & Resume API: Specifically designed for mobile environments, this allows apps to pause P2P swarms and RAG workspaces to meet background rules without losing model state - GPT-OSS Compatibility: Added support for the latest GPT-OSS models loaded externally, expanding the range of open-source intelligence available on the platform Build the future of private, unstoppable AI:
1:11

QVAC SDK 0.10.0 is now live, bringing advanced local compute capabilities and specialized hardware optimization directly to your device Key Features and Updates: - Image-to-Image Diffusion: Transform and edit images using simple prompts with 100% local computeā€”no cloud uploads or external servers required - Dynamic Tooling & KV Cache Management:Your local LLM now receives a tailored toolbox for every interaction, with automatic KV cache clearing to maintain high-speed inference - Doctor CLI: A new diagnostic tool that analyzes your hardware and memory, providing specific instructions on how to optimize your GPU for local AI - Suspend & Resume API: Specifically designed for mobile environments, this allows apps to pause P2P swarms and RAG workspaces to meet background rules without losing model state - GPT-OSS Compatibility: Added support for the latest GPT-OSS models loaded externally, expanding the range of open-source intelligence available on the platform Build the future of private, unstoppable AI:

QVAC

34,508 Aufrufe ā€¢ vor 3 Monaten

QVAC SDK 0.15.0 is live. This release adds multiple prompts batching, brings a native AMD GPU backend to the stack, moves more vision encoders onto mobile GPUs, and adds a second local coding-agent integration. Main highlights: - Prompt batching for the LLM addon. Batch multiple prompts into one job and process them concurrently, with each answer returned the moment its generation finishes. - Native AMD GPU backend. A first-class HIP/ROCm backend in @qvac/vla-ggml, auto-selected over Vulkan with clean fallback when ROCm is absent. - A second local coding agent. OpenClaw joins OpenCode for local, cloud-free agent workflows. AGENTS - OpenCode plugin update (@qvac/opencode-plugin). Aligned with the current SDK, CLI, and AI SDK provider packages. A fresh install runs OpenCode against managed local QVAC models out of the box, from the default qvac/qwen3.5-9b, with no manual qvac serve setup. - OpenClaw plugin (@qvac/openclaw-plugin). A second coding-agent integration alongside OpenCode. A fresh setup installs the plugin, creates a local qvac provider through onboarding, and runs a QVAC model through OpenClawšŸ¦ž's local service path. LANGUAGE MODELS - Prompt batching (LLM addon). Batch multiple prompts in one job and run them concurrently, each answer returns the moment its generation finishes, no waiting on the others. - Reasoning-context trimming on hybrid + recurrent models (@qvac/llm-llamacpp). remove_thinking_from_context now works beyond pure-attention models. Same JS API, no throw. VOICE AND SPEECH - Transcription (transcription-parakeet 0.9.0). More robust CPU fallback on GPU failure and a faster Vulkan backend on Pixel 9. - Text-to-speech features (tts-ggml 0.4.0). Adds LavaSR for noise removal and adjustable output frequency up to 48 kHz, plus Japanese via Chatterbox. - Text-to-speech fixes (tts-ggml 0.4.1). CPU fallback on GPU failure, a q8_0 KV crash fix on Metal with Chatterbox. VISION - Qwen3.5 vision encoder on GPU (Android). Image encoder moves onto the phone GPU, with a smarter tile-grid preprocessor and default image-token caps, for flagship Android: Vulkan on Mali (Pixel 9 Pro) and OpenCL on Adreno 830 (Galaxy S25). - Gemma-4 vision encoder on GPU (Android). Vision encoder runs on the phone GPU instead of CPU, same flagship Android targets. PLATFORM AND PERFORMANCE - AMD GPU backend (@qvac/vla-ggml). Native HIP/ROCm backend, auto-selected over Vulkan with clean fallback when ROCm is absent (Linux x64 only). Comes with ~23% faster than Vulkan, ~14% faster than PyTorch-ROCm, parity preserved. Unified code style. A cleaner, more consistent, easier-to-contribute codebase. Let's build. npm install @qvac/sdk
1:25

QVAC SDK 0.15.0 is live. This release adds multiple prompts batching, brings a native AMD GPU backend to the stack, moves more vision encoders onto mobile GPUs, and adds a second local coding-agent integration. Main highlights: - Prompt batching for the LLM addon. Batch multiple prompts into one job and process them concurrently, with each answer returned the moment its generation finishes. - Native AMD GPU backend. A first-class HIP/ROCm backend in @qvac/vla-ggml, auto-selected over Vulkan with clean fallback when ROCm is absent. - A second local coding agent. OpenClaw joins OpenCode for local, cloud-free agent workflows. AGENTS - OpenCode plugin update (@qvac/opencode-plugin). Aligned with the current SDK, CLI, and AI SDK provider packages. A fresh install runs OpenCode against managed local QVAC models out of the box, from the default qvac/qwen3.5-9b, with no manual qvac serve setup. - OpenClaw plugin (@qvac/openclaw-plugin). A second coding-agent integration alongside OpenCode. A fresh setup installs the plugin, creates a local qvac provider through onboarding, and runs a QVAC model through OpenClawšŸ¦ž's local service path. LANGUAGE MODELS - Prompt batching (LLM addon). Batch multiple prompts in one job and run them concurrently, each answer returns the moment its generation finishes, no waiting on the others. - Reasoning-context trimming on hybrid + recurrent models (@qvac/llm-llamacpp). remove_thinking_from_context now works beyond pure-attention models. Same JS API, no throw. VOICE AND SPEECH - Transcription (transcription-parakeet 0.9.0). More robust CPU fallback on GPU failure and a faster Vulkan backend on Pixel 9. - Text-to-speech features (tts-ggml 0.4.0). Adds LavaSR for noise removal and adjustable output frequency up to 48 kHz, plus Japanese via Chatterbox. - Text-to-speech fixes (tts-ggml 0.4.1). CPU fallback on GPU failure, a q8_0 KV crash fix on Metal with Chatterbox. VISION - Qwen3.5 vision encoder on GPU (Android). Image encoder moves onto the phone GPU, with a smarter tile-grid preprocessor and default image-token caps, for flagship Android: Vulkan on Mali (Pixel 9 Pro) and OpenCL on Adreno 830 (Galaxy S25). - Gemma-4 vision encoder on GPU (Android). Vision encoder runs on the phone GPU instead of CPU, same flagship Android targets. PLATFORM AND PERFORMANCE - AMD GPU backend (@qvac/vla-ggml). Native HIP/ROCm backend, auto-selected over Vulkan with clean fallback when ROCm is absent (Linux x64 only). Comes with ~23% faster than Vulkan, ~14% faster than PyTorch-ROCm, parity preserved. Unified code style. A cleaner, more consistent, easier-to-contribute codebase. Let's build. npm install @qvac/sdk

QVAC

29,259,075 Aufrufe ā€¢ vor 1 Monat

QVAC SDK 0.13.0 is live, and this version brings a lot of exciting updates! Local AI now plugs into your coding agent, ships as a desktop app in one command, and runs even more models. Highlights: NEW INTEGRATIONS - OpenCode and coding agents: the new @qvac/ai-sdk-provider makes QVAC a local provider. Less setup, same-model requests queue cleanly, and managed mode starts and supervises qvac serve for you. - Broader OpenAI-compatible API, validated across supported flows so covered capabilities stay consistent and testable. - Turn your QVAC project into a real desktop app for Mac, Windows, or Linux with a single command. The new Electron plugin handles the packaging and keeps the app small by including only what it needs. NEW MODELS - New pi0.5 model support - run a vision-language "robot brain" on a single ordinary graphics card, at full accuracy. - Image-to-video, fully local, via the Wan2.1 model in the Diffusion addon. - New BCI add-on: brain-computer interface transcription, fully local. Decode recorded neural signals into text on-device via the Whisper.cpp-based BCI model. IMPROVEMENTS - Whisper GPU transcription on Android, auto-picking the best backend (OpenCL on Adreno 700+, Vulkan elsewhere), unified on one ggml engine. - Parakeet steadier on mobile, with real end-of-utterance detection for streaming. - Supertonic TTS now runs full GPU across Metal, Vulkan, and OpenCL, with native streaming.
1:39

QVAC SDK 0.13.0 is live, and this version brings a lot of exciting updates! Local AI now plugs into your coding agent, ships as a desktop app in one command, and runs even more models. Highlights: NEW INTEGRATIONS - OpenCode and coding agents: the new @qvac/ai-sdk-provider makes QVAC a local provider. Less setup, same-model requests queue cleanly, and managed mode starts and supervises qvac serve for you. - Broader OpenAI-compatible API, validated across supported flows so covered capabilities stay consistent and testable. - Turn your QVAC project into a real desktop app for Mac, Windows, or Linux with a single command. The new Electron plugin handles the packaging and keeps the app small by including only what it needs. NEW MODELS - New pi0.5 model support - run a vision-language "robot brain" on a single ordinary graphics card, at full accuracy. - Image-to-video, fully local, via the Wan2.1 model in the Diffusion addon. - New BCI add-on: brain-computer interface transcription, fully local. Decode recorded neural signals into text on-device via the Whisper.cpp-based BCI model. IMPROVEMENTS - Whisper GPU transcription on Android, auto-picking the best backend (OpenCL on Adreno 700+, Vulkan elsewhere), unified on one ggml engine. - Parakeet steadier on mobile, with real end-of-utterance detection for streaming. - Supertonic TTS now runs full GPU across Metal, Vulkan, and OpenCL, with native streaming.

QVAC

20,931,912 Aufrufe ā€¢ vor 2 Monaten

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.
20:45

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

h100envy

702,669 Aufrufe ā€¢ vor 28 Tagen

Superior methodology beats raw parameter count. šŸ§  Introducing QVAC MedPsy: Local-first medical AI that redefines the possible. 1/ Unprecedented Power: MedPsy 1.7B model outperforms Googleā€™s MedGemma 4B by 11 points and our 4B model beats MedGemma 27B on real-world health benchmarks. 2/ Extreme Efficiency: 3.2x fewer tokens means near-instant inference on your phone or wearable. 3/ Absolute Privacy: Expert-level reasoning running 100% locally. No data leaves your device. We arenā€™t simply shrinking models; weā€™re anchoring intelligence where it matters most. High-level medical logic is now a sovereign right. The future of healthcare is local. Learn more:
2:16

Superior methodology beats raw parameter count. šŸ§  Introducing QVAC MedPsy: Local-first medical AI that redefines the possible. 1/ Unprecedented Power: MedPsy 1.7B model outperforms Googleā€™s MedGemma 4B by 11 points and our 4B model beats MedGemma 27B on real-world health benchmarks. 2/ Extreme Efficiency: 3.2x fewer tokens means near-instant inference on your phone or wearable. 3/ Absolute Privacy: Expert-level reasoning running 100% locally. No data leaves your device. We arenā€™t simply shrinking models; weā€™re anchoring intelligence where it matters most. High-level medical logic is now a sovereign right. The future of healthcare is local. Learn more:

QVAC

2,416,342 Aufrufe ā€¢ vor 3 Monaten

QVAC SDK 0.14.0 is live. This release makes the on-device stack faster on mobile, ships the developer-agent path, and takes local text-to-speech to 31 languages. Main highlights: - OpenCode and OpenClaw. The first official OpenCode plugin, plus a maintained OpenClaw compatibility path, both built on managed mode and qvac serve. Point a coding agent at a local model with far less setup and far fewer surprises. - Brain-computer interface transcription, on the SDK. Take recorded neural signal data and decode it into text, fully on-device, no cloud. Stream it in chunks through a simple API. In 0.14 it runs GPU-accelerated on iOS. - Text to Speech in 31 languages with our Supertonic3 upgrade. VOICE AND SPEECH - Supertonic3 multilingual TTS, 5 languages to 31. - Chatterbox and Supertonic now run on the Android GPU, with lower memory use (especially on iOS), quantized s3gen Chatterbox support, and a fix for Chatterbox occasionally emitting random speech. - Whisper transcription now runs on the iOS GPU. Parakeet runs on the Android GPU, with steadier real-time streaming. VISION AND OCR - VLM multi-tile batching: high-resolution Pan and Scan images are encoded in one pass instead of tile by tile, for faster vision throughput. - OCR on ggml (EasyOCR and DocTR) reaches full speed parity with the onnx path, across Metal, OpenCL, and Vulkan. PLATFORM AND RELIABILITY - Dynamic compute backends on Linux: one build picks the right backend at runtime, and opens the door to ROCm and CUDA support without per-backend builds. - Thinking tokens are kept out of the model context, so reasoning no longer fills the KV cache. SDK 0.14.0 is now leaner and faster to start. Letā€™s build.
1:51

QVAC SDK 0.14.0 is live. This release makes the on-device stack faster on mobile, ships the developer-agent path, and takes local text-to-speech to 31 languages. Main highlights: - OpenCode and OpenClaw. The first official OpenCode plugin, plus a maintained OpenClaw compatibility path, both built on managed mode and qvac serve. Point a coding agent at a local model with far less setup and far fewer surprises. - Brain-computer interface transcription, on the SDK. Take recorded neural signal data and decode it into text, fully on-device, no cloud. Stream it in chunks through a simple API. In 0.14 it runs GPU-accelerated on iOS. - Text to Speech in 31 languages with our Supertonic3 upgrade. VOICE AND SPEECH - Supertonic3 multilingual TTS, 5 languages to 31. - Chatterbox and Supertonic now run on the Android GPU, with lower memory use (especially on iOS), quantized s3gen Chatterbox support, and a fix for Chatterbox occasionally emitting random speech. - Whisper transcription now runs on the iOS GPU. Parakeet runs on the Android GPU, with steadier real-time streaming. VISION AND OCR - VLM multi-tile batching: high-resolution Pan and Scan images are encoded in one pass instead of tile by tile, for faster vision throughput. - OCR on ggml (EasyOCR and DocTR) reaches full speed parity with the onnx path, across Metal, OpenCL, and Vulkan. PLATFORM AND RELIABILITY - Dynamic compute backends on Linux: one build picks the right backend at runtime, and opens the door to ROCm and CUDA support without per-backend builds. - Thinking tokens are kept out of the model context, so reasoning no longer fills the KV cache. SDK 0.14.0 is now leaner and faster to start. Letā€™s build.

QVAC

23,973,950 Aufrufe ā€¢ vor 1 Monat