Loading video...

Video Failed to Load

Go Home

LFM2-2.6B-Transcript AMD🤝Liquid AI > Private, on-device meeting summarization > Cloud-level quality > Faster processing, lower memory footprint > Runs across CPU, GPU, and NPU on AMD Ryzen AI PC Great showcase of what tiny models can achieve when fine-tuned

maximelabonne's profile picture

Maxime Labonne

33,414 subscribers

28,034 views • 9 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

The AMD advantage in agentic AI is architectural. See how AMD Ryzen AI combines CPU, GPU, and unified memory for end-to-end agent workflows. Learn more:
0:54

The AMD advantage in agentic AI is architectural. See how AMD Ryzen AI combines CPU, GPU, and unified memory for end-to-end agent workflows. Learn more:

AMD Ryzen

20,539 views • 2 months ago

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026
2:47

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026

Mike

16,121 views • 5 months ago

One shot builds aren’t cloud only. Qwen 3.8 Flash plans the build, then hands it to Qwen 3.8 27B, all running locally across the GPU, CPU and 128GB of unified memory on one AMD Ryzen AI Max+ processor. Now, we iterate. See how Ryzen AI Max+ helps you build.
0:41

One shot builds aren’t cloud only. Qwen 3.8 Flash plans the build, then hands it to Qwen 3.8 27B, all running locally across the GPU, CPU and 128GB of unified memory on one AMD Ryzen AI Max+ processor. Now, we iterate. See how Ryzen AI Max+ helps you build.

AMD Ryzen

17,829 views • 1 month ago

Bringing AI agents to the PC requires efficiency, speed, and smart memory management. AMD and Liquid AI are partnering to enable foundational models on PCs and end-point devices to address the real-world challenges of running AI agents locally. Liquid AI Co-founder and CEO Ramin explains how we are helping make on-device AI practical and accessible.
0:47

Bringing AI agents to the PC requires efficiency, speed, and smart memory management. AMD and Liquid AI are partnering to enable foundational models on PCs and end-point devices to address the real-world challenges of running AI agents locally. Liquid AI Co-founder and CEO Ramin explains how we are helping make on-device AI practical and accessible.

AMD

20,936 views • 8 months ago

The future of AI runs across local devices and the cloud. @JackHuynh, AMD SVP and GM of the Computing and Graphics Group, explains how Ryzen AI Halo gives developers more room to experiment with models locally. Watch to hear his vision for what comes next.
0:50

The future of AI runs across local devices and the cloud. @JackHuynh, AMD SVP and GM of the Computing and Graphics Group, explains how Ryzen AI Halo gives developers more room to experiment with models locally. Watch to hear his vision for what comes next.

AMD

22,020 views • 16 days ago

CPU Demo In Action: Meta Llama 3 8b Instruct With AMD Ryzen AI
1:00

CPU Demo In Action: Meta Llama 3 8b Instruct With AMD Ryzen AI

AMD

39,226 views • 2 years ago

Introducing AMD Ryzen AI Halo, an Agent Computer built to make local AI development fast and simple. • Ryzen AI Developer Center pre-installed • Pre-optimized from first power on • Built to reduce setup friction • Designed for local AI development AMD Ryzen AI Halo brings AI from the cloud into the hands of developers with Ryzen AI developer center pre-installed and optimized from first power on, developers can hit the ground running.
1:07

Introducing AMD Ryzen AI Halo, an Agent Computer built to make local AI development fast and simple. • Ryzen AI Developer Center pre-installed • Pre-optimized from first power on • Built to reduce setup friction • Designed for local AI development AMD Ryzen AI Halo brings AI from the cloud into the hands of developers with Ryzen AI developer center pre-installed and optimized from first power on, developers can hit the ground running.

AMD

26,118 views • 5 months ago

running Claude Code w/ local models on my own GPUs at home > vLLM serving GLM-4.5 Air > on 4x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-to-end on my AI cluster this is what local AI actually looks like Buy a GPU
1:57

running Claude Code w/ local models on my own GPUs at home > vLLM serving GLM-4.5 Air > on 4x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-to-end on my AI cluster this is what local AI actually looks like Buy a GPU

Ahmad

262,712 views • 9 months ago

IN: video fine-tuning support for AI at Meta's V-JEPA 2 in HF transformers 🔥 it comes with > fine-tuning notebook > four models fine-tuned on Diving48 and SSv2 dataset > FastRTC demo on V-JEPA2 SSv2 (see below) we're looking forward to see fine-tuned V-JEPA2 models on Hub ⏯️
0:36

IN: video fine-tuning support for AI at Meta's V-JEPA 2 in HF transformers 🔥 it comes with > fine-tuning notebook > four models fine-tuned on Diving48 and SSv2 dataset > FastRTC demo on V-JEPA2 SSv2 (see below) we're looking forward to see fine-tuned V-JEPA2 models on Hub ⏯️

merve

16,733 views • 1 year ago

192GB of unified memory, up to 160GB of it for the GPU: the HP ZBook Ultra G3a 16 has the most GPU memory we've seen on an AMD Ryzen AI Max system. New 100W thermal design (55W on the G1a), 96Wh battery, Gen5 slot to 8TB, 4.2 lb. #HPZBook #LocalAI #Workstation HP Z Workstations & Solutions AMD Ryzen
2:49

192GB of unified memory, up to 160GB of it for the GPU: the HP ZBook Ultra G3a 16 has the most GPU memory we've seen on an AMD Ryzen AI Max system. New 100W thermal design (55W on the G1a), 96Wh battery, Gen5 slot to 8TB, 4.2 lb. #HPZBook #LocalAI #Workstation HP Z Workstations & Solutions AMD Ryzen

StorageReview.com

66,568 views • 1 month 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.
0:54

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 • 1 year ago

Fable PC specs revealed - what works for you? 🔹LOW Target: 1080p - 30FPS CPU: AMD Ryzen 5 2600 / Intel i7 6850K GPU: NVIDIA RTX 5050 / NVIDIA RTX 2060 / AMD RX 6600 / Intel A580 VRAM: 6GB RAM: 12GB 🔹MEDIUM (RECOMMENDED) Target: 1440p - 30FPS / 1200p - 60FPS CPU: AMD Ryzen 5 5600 / Intel i5 11600KF GPU: NVIDIA RTX 5060 / NVIDIA RTX 3060Ti / AMD RX 9060XT / AMD RX 6700XT VRAM: 8GB RAM: 16GB 🔹HIGH Target: 1440p - 60FPS CPU: AMD Ryzen 7 7700X / Intel i7 12700K GPU: NVIDIA RTX 5070 / NVIDIA RTX 3080Ti / AMD RX 9070 / AMD RX 7900XT VRAM: 12GB RAM: 16GB 🔹ULTRA Target: 4K - 60FPS CPU: AMD Ryzen 9 7900X / Intel i9 13900K GPU: NVIDIA RTX 5080 / NVIDIA RTX 4080 VRAM: 16GB RAM: 16GB Operating System: WINDOWS 10 22H2 Storage: SSD
0:48

Fable PC specs revealed - what works for you? 🔹LOW Target: 1080p - 30FPS CPU: AMD Ryzen 5 2600 / Intel i7 6850K GPU: NVIDIA RTX 5050 / NVIDIA RTX 2060 / AMD RX 6600 / Intel A580 VRAM: 6GB RAM: 12GB 🔹MEDIUM (RECOMMENDED) Target: 1440p - 30FPS / 1200p - 60FPS CPU: AMD Ryzen 5 5600 / Intel i5 11600KF GPU: NVIDIA RTX 5060 / NVIDIA RTX 3060Ti / AMD RX 9060XT / AMD RX 6700XT VRAM: 8GB RAM: 16GB 🔹HIGH Target: 1440p - 60FPS CPU: AMD Ryzen 7 7700X / Intel i7 12700K GPU: NVIDIA RTX 5070 / NVIDIA RTX 3080Ti / AMD RX 9070 / AMD RX 7900XT VRAM: 12GB RAM: 16GB 🔹ULTRA Target: 4K - 60FPS CPU: AMD Ryzen 9 7900X / Intel i9 13900K GPU: NVIDIA RTX 5080 / NVIDIA RTX 4080 VRAM: 16GB RAM: 16GB Operating System: WINDOWS 10 22H2 Storage: SSD

SpawnYaard 🎮

36,266 views • 2 months ago

ICYMI: AI is going local. AMD and Liquid AI are enabling on-device agents that are more secure and efficient. Watch the latest Advanced Insights episode to learn more:
0:56

ICYMI: AI is going local. AMD and Liquid AI are enabling on-device agents that are more secure and efficient. Watch the latest Advanced Insights episode to learn more:

AMD

19,573 views • 6 months ago

Character Showcase | Papasha >> Download on mobile and PC: #GirlsFrontline2Exilium #gfl2exilium
0:35

Character Showcase | Papasha >> Download on mobile and PC: #GirlsFrontline2Exilium #gfl2exilium

GIRLS' FRONTLINE 2: EXILIUM-EN Official

112,001 views • 1 year ago

Laya plays Plants vs Zombies on CPU 🧟 We patched the llama.cpp engine to run Laya natively so it works on a regular CPU with no GPU and here a fine-tuned Laya makes every move until it beats the Plants vs Zombies pool level Run decision models locally->
0:55

Laya plays Plants vs Zombies on CPU 🧟 We patched the llama.cpp engine to run Laya natively so it works on a regular CPU with no GPU and here a fine-tuned Laya makes every move until it beats the Plants vs Zombies pool level Run decision models locally->

atomic.chat

14,071 views • 1 month ago

AMD on local AI: "this is the smallest AI development system in the world, capable of running models up to 200 billion parameters locally, not connected to anything" 128GB of unified memory shared by CPU, GPU, and NPU fits in your hand. Runs a model larger than GPT-3 with no internet $3,999 once. roughly $16 a month in power Cloud equivalent: up to $750 a month The question was never whether local AI could compete on power It was whether it could compete on price. Now it does
1:00

AMD on local AI: "this is the smallest AI development system in the world, capable of running models up to 200 billion parameters locally, not connected to anything" 128GB of unified memory shared by CPU, GPU, and NPU fits in your hand. Runs a model larger than GPT-3 with no internet $3,999 once. roughly $16 a month in power Cloud equivalent: up to $750 a month The question was never whether local AI could compete on power It was whether it could compete on price. Now it does

plutos

152,392 views • 4 months ago

you can create full daily vlogs with AI for PENNIES WAN 3.0 is now UNLIMITED on Higgsfield, delivering Seedance 2.5 level quality at 9x lower cost >WAN 3.0 - $0.042/sec >Seedance 2.5 - $0.3862/sec
0:27

you can create full daily vlogs with AI for PENNIES WAN 3.0 is now UNLIMITED on Higgsfield, delivering Seedance 2.5 level quality at 9x lower cost >WAN 3.0 - $0.042/sec >Seedance 2.5 - $0.3862/sec

MAX

53,623 views • 19 days ago