Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

LFM2-VL support with GGUF and llama.cpp 🥳 You can now run these tiny, hyper-efficient VLMs on your watch! We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on Hugging Face

Maxime Labonne

26,103 subscribers

19,947 views • 11 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

Maxime Labonne

85,053 views • 10 months ago

LFM2-8B-A1B just dropped on Hugging Face! 8.3B params with only 1.5B active/token 🚀 > Quality ≈ 3–4B dense, yet faster than Qwen3-1.7B > MoE designed to run on phones/laptops (llama.cpp / vLLM) > Pre-trained on 12T tokens → strong math/code/IF

LFM2-8B-A1B just dropped on Hugging Face! 8.3B params with only 1.5B active/token 🚀 > Quality ≈ 3–4B dense, yet faster than Qwen3-1.7B > MoE designed to run on phones/laptops (llama.cpp / vLLM) > Pre-trained on 12T tokens → strong math/code/IF

Maxime Labonne

40,714 views • 10 months ago

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Xenova

48,777 views • 4 months ago

Advice for AI engineers 💡 Browser control is possible with a Small Model, like LFM2-350M by Liquid AI . Here's a 60-minute deep dive on how to fine-tune with RL and OpenEnv by Hugging Face Enjoy ↓

Advice for AI engineers 💡 Browser control is possible with a Small Model, like LFM2-350M by Liquid AI . Here's a 60-minute deep dive on how to fine-tune with RL and OpenEnv by Hugging Face Enjoy ↓

Pau Labarta Bajo

16,169 views • 3 months ago

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓

Pau Labarta Bajo

80,258 views • 5 months ago

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Pascale Fung

90,144 views • 7 months ago

Advice for AI engineers 💡 A local AI assistant is just a while loop, an LLM and a set of tools. Here's a step-by-step lesson on how to build one from scratch with Liquid AI LFM2-24B-A2B running on llama.cpp. No cloud APIs. Enjoy ↓

Advice for AI engineers 💡 A local AI assistant is just a while loop, an LLM and a set of tools. Here's a step-by-step lesson on how to build one from scratch with Liquid AI LFM2-24B-A2B running on llama.cpp. No cloud APIs. Enjoy ↓

Pau Labarta Bajo

15,463 views • 3 months ago

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

NEXA AI

26,091 views • 9 months ago

locate-anything.cpp: native C++/ggml (ggml) inference for NVIDIA's LocateAnything-3B, open-vocabulary object detection / visual grounding, one of the neat detection VLMs out there, from the LocalAI team. Same detections as the official model, now running anywhere with no Python and faster, on CPU and GPU. Quantized GGUF on Hugging Face 🤗 Huge thanks to Georgi Gerganov for ggml and to NVIDIAAI for releasing LocateAnything! 🧵

locate-anything.cpp: native C++/ggml (ggml) inference for NVIDIA's LocateAnything-3B, open-vocabulary object detection / visual grounding, one of the neat detection VLMs out there, from the LocalAI team. Same detections as the official model, now running anywhere with no Python and faster, on CPU and GPU. Quantized GGUF on Hugging Face 🤗 Huge thanks to Georgi Gerganov for ggml and to NVIDIAAI for releasing LocateAnything! 🧵

Ettore Di Giacinto

13,972 views • 1 month ago

Document Querying with Qwen2-VL-7B and JSON Output Complete video: I demonstrate how to perform document queries using Qwen2-VL-7B. By simplifying field names, we streamline the prompts, making them more efficient and reusable across different documents. This approach is similar to running SQL queries on a database, but tailored for language models like Qwen2-VL-7B, with results returned in JSON format. Qwen #MultimodalLLM #OCR

Document Querying with Qwen2-VL-7B and JSON Output Complete video: I demonstrate how to perform document queries using Qwen2-VL-7B. By simplifying field names, we streamline the prompts, making them more efficient and reusable across different documents. This approach is similar to running SQL queries on a database, but tailored for language models like Qwen2-VL-7B, with results returned in JSON format. Qwen #MultimodalLLM #OCR

Andrej Baranovskij

15,976 views • 1 year ago

Introducing the EASIEST way to fine-tune Qwen 2 VL with a Hugging Face dataset! (Link to repo in first reply). You can either fine-tune inside or a Gradio app or with a single line of Python. Simply select your favorite image-text dataset and fine-tune! A special thanks to Faen Zhang and all those at HuggingFace and those behind Qwen 2 VL. blog coming soon!

Introducing the EASIEST way to fine-tune Qwen 2 VL with a Hugging Face dataset! (Link to repo in first reply). You can either fine-tune inside or a Gradio app or with a single line of Python. Simply select your favorite image-text dataset and fine-tune! A special thanks to Faen Zhang and all those at HuggingFace and those behind Qwen 2 VL. blog coming soon!

William J.B. Mattingly

21,466 views • 1 year ago

Laguna S 2.1 is built to run locally. We heard the ask for a serious open model in the 80–120B range. Laguna S 2.1 is our answer, and we want it to redefine what this size class can do. Weights ship in BF16, FP8, INT4 and NVFP4, with official GGUF and MLX conversions, plus official DFlash draft models for faster inference. Day-one support across llama.cpp, ollama, Valerie Lee Make Up, SGLang, NVIDIA TRT-LLM, Hugging Face transformers and ZML. Watch it run on an NVIDIA AI DGX Spark.

Laguna S 2.1 is built to run locally. We heard the ask for a serious open model in the 80–120B range. Laguna S 2.1 is our answer, and we want it to redefine what this size class can do. Weights ship in BF16, FP8, INT4 and NVFP4, with official GGUF and MLX conversions, plus official DFlash draft models for faster inference. Day-one support across llama.cpp, ollama, Valerie Lee Make Up, SGLang, NVIDIA TRT-LLM, Hugging Face transformers and ZML. Watch it run on an NVIDIA AI DGX Spark.

Poolside

31,242 views • 13 days ago

Introducing Vision Arena! Inspired by the awesome Chatbot Arena, we built a web demo on Hugging Face for testing Vision LMs (GPT-4V, Gemini, Llava, Qwen-VL, etc.). You can easily test two VLMs side by side and vote! It’s still a work-in-progress. Feedbacks are welcome! 🔗 Kudos to the main contributor Yujie Lu (Yujie Lu), and the team: Dongfu Jiang Wenhu Chen Ai2 ; Thanks to LMSYS Org’s great code & design!

Introducing Vision Arena! Inspired by the awesome Chatbot Arena, we built a web demo on Hugging Face for testing Vision LMs (GPT-4V, Gemini, Llava, Qwen-VL, etc.). You can easily test two VLMs side by side and vote! It’s still a work-in-progress. Feedbacks are welcome! 🔗 Kudos to the main contributor Yujie Lu (Yujie Lu), and the team: Dongfu Jiang Wenhu Chen Ai2 ; Thanks to LMSYS Org’s great code & design!

Bill Yuchen Lin

146,020 views • 2 years ago

We just added speculative decoding for Carbon, so you can now generate DNA sequences 2-3x faster with llama.cpp This enables anyone to process huge genomes locally! GGUF weights and quants:

We just added speculative decoding for Carbon, so you can now generate DNA sequences 2-3x faster with llama.cpp This enables anyone to process huge genomes locally! GGUF weights and quants:

Lewis Tunstall

15,991 views • 2 months ago

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

Qwen

762,450 views • 1 year ago

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.

👋 Jan

17,759 views • 10 months ago

We've partnered to bring more Gemma 3 quantized models to you! 🚀 We worked with Georgi Gerganov llama.cpp, LM Studio, MLX, ollama to make sure you can run it using your favorite tool! Gemma models optimized with QAT, reduce memory requirements while keeping quality! All models checkpoints are available on Hugging Face and Kaggle. 🤗 What does this mean? - Gemma 3 27B (int4): Fits on NVIDIA RTX 3090 (24GB VRAM) or similar. - Gemma 3 12B (int4): Only needs a NVIDIA RTX 4060 (8GB VRAM) or similar. - Gemma 3 4B, 1B (int4): Run anything with more than 2.5GB Memory. Want to see it in action? Video below shows how easy it is to get started using LMStudio:

We've partnered to bring more Gemma 3 quantized models to you! 🚀 We worked with Georgi Gerganov llama.cpp, LM Studio, MLX, ollama to make sure you can run it using your favorite tool! Gemma models optimized with QAT, reduce memory requirements while keeping quality! All models checkpoints are available on Hugging Face and Kaggle. 🤗 What does this mean? - Gemma 3 27B (int4): Fits on NVIDIA RTX 3090 (24GB VRAM) or similar. - Gemma 3 12B (int4): Only needs a NVIDIA RTX 4060 (8GB VRAM) or similar. - Gemma 3 4B, 1B (int4): Run anything with more than 2.5GB Memory. Want to see it in action? Video below shows how easy it is to get started using LMStudio:

Philipp Schmid

15,996 views • 1 year ago

just landed on hugging face: Step1X-Edit ✍️ & it's honestly one of the best open source image editors I've tried ✨ combines Multimodal LLM (Qwen VL) with Diffusion transformers to process and perform edit instructions ✨ apache 2.0 license ✨ new benchmark for image editing: GEdit-Bench

just landed on hugging face: Step1X-Edit ✍️ & it's honestly one of the best open source image editors I've tried ✨ combines Multimodal LLM (Qwen VL) with Diffusion transformers to process and perform edit instructions ✨ apache 2.0 license ✨ new benchmark for image editing: GEdit-Bench

Linoy Tsaban

56,525 views • 1 year ago

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: Blog and Guide: Available now on Hugging Face, NVIDIA, Docker and Colab.

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: Blog and Guide: Available now on Hugging Face, NVIDIA, Docker and Colab.

Unsloth AI

1,723,362 views • 4 months ago