正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Casually running a 180B parameter LLM on M2 Ultra

Georgi Gerganov

62,252 subscribers

683,207 次观看 • 2 年前 •via X (Twitter)

科学技术教育艺术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

🌟 Introducing Falcon 180B: The World's Most Powerful Open LLM! 🚀 At #TII, we are continuing to push the boundaries of generative AI with our open access Falcon 180B AI model which has already soared to the top of the Hugging Face Leaderboard.

🌟 Introducing Falcon 180B: The World's Most Powerful Open LLM! 🚀 At #TII, we are continuing to push the boundaries of generative AI with our open access Falcon 180B AI model which has already soared to the top of the Hugging Face Leaderboard.

Technology Innovation Institute

1,296,137 次观看 • 2 年前

Full F16 precision 34B Code Llama at >20 t/s on M2 Ultra

Full F16 precision 34B Code Llama at >20 t/s on M2 Ultra

Georgi Gerganov

1,157,414 次观看 • 2 年前

The video is a Llama v1 7B model implemented in MLX and running on an M2 Ultra. More here: * Train a Transformer LM or fine-tune with LoRA * Text generation with Mistral * Image generation with Stable Diffusion * Speech recognition with Whisper

The video is a Llama v1 7B model implemented in MLX and running on an M2 Ultra. More here: * Train a Transformer LM or fine-tune with LoRA * Text generation with Mistral * Image generation with Stable Diffusion * Speech recognition with Whisper

Awni Hannun

66,565 次观看 • 2 年前

TENCENT casually dropping a 13bn parameter open sourced video model WITH weights 🩵 Looks unreal and can't wait to test it

TENCENT casually dropping a 13bn parameter open sourced video model WITH weights 🩵 Looks unreal and can't wait to test it

A.I.Warper

156,356 次观看 • 1 年前

What would it look like to combine Google search (shallow Knowledge Graph reasoning over an ultra-ultra-wide index) with LLM in-context learning (highly intelligent operations on a tiny index)?

What would it look like to combine Google search (shallow Knowledge Graph reasoning over an ultra-ultra-wide index) with LLM in-context learning (highly intelligent operations on a tiny index)?

Dwarkesh Patel

100,546 次观看 • 1 年前

Bro is casually out running a nuclear blast

Bro is casually out running a nuclear blast

Anime Posts

4,215,305 次观看 • 2 个月前

This looks like a test drive unit of the BMW M2. The driver is casually doing donuts on a busy public road in Noida, not cool, it’s reckless.

This looks like a test drive unit of the BMW M2. The driver is casually doing donuts on a busy public road in Noida, not cool, it’s reckless.

AARIZ RIZVI

747,357 次观看 • 1 年前

Agentic LLM NPCs with multi-user conversation all running on consumer-grade local hardware

Agentic LLM NPCs with multi-user conversation all running on consumer-grade local hardware

stochastics

24,261 次观看 • 1 年前

What a way to close out the Ultra afterparty at M2 Miami B2B with the amazing Nicole Moudaber. That’s a wrap on Miami Music Week! 🖤

What a way to close out the Ultra afterparty at M2 Miami B2B with the amazing Nicole Moudaber. That’s a wrap on Miami Music Week! 🖤

Carl Cox

21,272 次观看 • 1 年前

EMF Radiation Test Shows Sitting in an Electric Car is Like Standing Near a Running Microwave - Cell Phone: 120 mW/m2 - Microwave: 360 mW/m2 - Microwave (1-2’ Away): 100 mW/m2 - Inside Tesla: 100 mW/m2 Full Video:

EMF Radiation Test Shows Sitting in an Electric Car is Like Standing Near a Running Microwave - Cell Phone: 120 mW/m2 - Microwave: 360 mW/m2 - Microwave (1-2’ Away): 100 mW/m2 - Inside Tesla: 100 mW/m2 Full Video:

Chief Nerd

105,325 次观看 • 3 年前

Finally found a meaningful scenario for running LLM in the browser, peering into the internals of LLM to see what's really happening inside

Finally found a meaningful scenario for running LLM in the browser, peering into the internals of LLM to see what's really happening inside

Broooooklyn

45,882 次观看 • 1 个月前

Bro is just casually out running a nuclear blast 💀

Bro is just casually out running a nuclear blast 💀

jass

1,430,022 次观看 • 5 天前

Try now Hyperfast LLM running on custom built GPUs Answers in miliseconds, not seconds How? 🤯

Try now Hyperfast LLM running on custom built GPUs Answers in miliseconds, not seconds How? 🤯

@levelsio

602,378 次观看 • 2 年前

An Ultra-Orthodox Jewish man casually takes a shit in the Armenian Quarter of Jerusalem.

Sensitive content

An Ultra-Orthodox Jewish man casually takes a shit in the Armenian Quarter of Jerusalem.

Clash Report

1,150,073 次观看 • 1 个月前

casually running into Peeves bullying students on their way to class in #HogwartLegacy 🤣

casually running into Peeves bullying students on their way to class in #HogwartLegacy 🤣

TmarTn

199,414 次观看 • 3 年前

I sent an AI computer to the edge of space! HAAID-1 was the first-of-its-kind high-altitude balloon mission. It reached an altitude of ~19 km and ran a 360M-parameter LLM on a Raspberry Pi at -68°C.

I sent an AI computer to the edge of space! HAAID-1 was the first-of-its-kind high-altitude balloon mission. It reached an altitude of ~19 km and ran a 360M-parameter LLM on a Raspberry Pi at -68°C.

Yatharth Mann

108,594 次观看 • 27 天前

Local voice AI with a 235 billion parameter LLM. ✅ - smart-turn v2 - MLX Whisper (large-v3-turbo-q4) - Qwen3-235B-A22B-Instruct-2507-3bit-DWQ - Kokoro All models running local on an M4 mac. Max RAM usage ~110GB. Voice-to-voice latency is ~950ms. There are a couple of relatively easy ways to carve another ~100ms off that number. But it's not a bad start!

Local voice AI with a 235 billion parameter LLM. ✅ - smart-turn v2 - MLX Whisper (large-v3-turbo-q4) - Qwen3-235B-A22B-Instruct-2507-3bit-DWQ - Kokoro All models running local on an M4 mac. Max RAM usage ~110GB. Voice-to-voice latency is ~950ms. There are a couple of relatively easy ways to carve another ~100ms off that number. But it's not a bad start!

kwindla

66,639 次观看 • 11 个月前

good morning /v1/chat/completions This is a test we ran overnight on TensorRT-LLM with modified kernels serving a custom 1B parameter model we trained for a customer ~200ms end-to-end latency (not TTFB, full request). Beats their current Cerebras stack on latency and quality

good morning /v1/chat/completions This is a test we ran overnight on TensorRT-LLM with modified kernels serving a custom 1B parameter model we trained for a customer ~200ms end-to-end latency (not TTFB, full request). Beats their current Cerebras stack on latency and quality

Sam Hogan 🇺🇸

43,655 次观看 • 4 个月前

Roman Reigns just casually whipping out Ultra Instinct in #WWE2K25 😮

Roman Reigns just casually whipping out Ultra Instinct in #WWE2K25 😮

GameVolt

105,926 次观看 • 6 个月前