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。

Nemotron 3 Nano runs nicely with mlx-lm on an M4 Max. Could be a great model for local use on Mac: MoE + hybrid attention make it fast even for very long context. Generating in realtime with 4-bit model:

Awni Hannun

44,902 subscribers

51,070 次观看 • 8 个月前 •via X (Twitter)

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

Llama 3.3 70B 4-bit runs nicely on a 64GB M3 Max with in MLX LM (~10 toks/sec). Would be even faster on an M4 Max. Yesterday's server-only 405B is today's laptop 70B:

Llama 3.3 70B 4-bit runs nicely on a 64GB M3 Max with in MLX LM (~10 toks/sec). Would be even faster on an M4 Max. Yesterday's server-only 405B is today's laptop 70B:

Awni Hannun

110,534 次观看 • 1 年前

A perfect coding model for MLX on Apple silicon.. Qwen delivered again. Runs quite fast on an M3 Ultra. Running the 4-bit quantized with mlx-lm:

A perfect coding model for MLX on Apple silicon.. Qwen delivered again. Runs quite fast on an M3 Ultra. Running the 4-bit quantized with mlx-lm:

Awni Hannun

186,772 次观看 • 1 年前

Qwen3-Coder-Flash runs quite fast on an M4 Max with mlx-lm. Running the 4-bit here, generated 4,467 tokens at >107 tokens/sec:

Qwen3-Coder-Flash runs quite fast on an M4 Max with mlx-lm. Running the 4-bit here, generated 4,467 tokens at >107 tokens/sec:

Awni Hannun

196,508 次观看 • 1 年前

DeepSeek R1 (the full 680B model) runs nicely in higher quality 4-bit on 3 M2 Ultras with MLX. Asked it a coding question and it thought for ~2k tokens and generated 3500 tokens overall:

DeepSeek R1 (the full 680B model) runs nicely in higher quality 4-bit on 3 M2 Ultras with MLX. Asked it a coding question and it thought for ~2k tokens and generated 3500 tokens overall:

Awni Hannun

997,247 次观看 • 1 年前

Made a demo to do test-time-scaling with mlx-lm and a R1-based reasoning model. Same idea as S1: - To force a response, swap "Wait" for "</think>" - To think more, swap "</think>" for "Wait" Runs fast with 4-bit Qwen 32B on an M3 max:

Made a demo to do test-time-scaling with mlx-lm and a R1-based reasoning model. Same idea as S1: - To force a response, swap "Wait" for "</think>" - To think more, swap "</think>" for "Wait" Runs fast with 4-bit Qwen 32B on an M3 max:

Awni Hannun

59,790 次观看 • 1 年前

QwQ-32B evals on par with Deep Seek R1 680B but runs fast on a laptop. Delivery accepted. Here it is running nicely on a M4 Max with MLX. A snippet of its 8k token long thought process:

QwQ-32B evals on par with Deep Seek R1 680B but runs fast on a laptop. Delivery accepted. Here it is running nicely on a M4 Max with MLX. A snippet of its 8k token long thought process:

Awni Hannun

132,388 次观看 • 1 年前

DeepSeek R1 (the 680B MOE) is ~20% faster in the latest mlx / mlx-lm. 4-bit model on 3 M2 Ultras generates 4k tokens at a respectable 15 toks/sec. Plus some QoL improvements: - Only downloads the local shard (much faster startup) - Distributed launcher ships with MLX

DeepSeek R1 (the 680B MOE) is ~20% faster in the latest mlx / mlx-lm. 4-bit model on 3 M2 Ultras generates 4k tokens at a respectable 15 toks/sec. Plus some QoL improvements: - Only downloads the local shard (much faster startup) - Distributed launcher ships with MLX

Awni Hannun

86,921 次观看 • 1 年前

Qwen3.5 runs quite well in mlx-lm. Awesome that we have a frontier-level hybrid model. The context gets longer but the inference speed and memory use barely change. Here's the Q4 generating a space invaders game on an M3 Ultra. Generated 4,120 tokens at 37.6 tok/s.

Qwen3.5 runs quite well in mlx-lm. Awesome that we have a frontier-level hybrid model. The context gets longer but the inference speed and memory use barely change. Here's the Q4 generating a space invaders game on an M3 Ultra. Generated 4,120 tokens at 37.6 tok/s.

Awni Hannun

48,673 次观看 • 5 个月前

GLM-4.7 runs quite well on an M3 Ultra with mlx-lm, even at a near lossless precision (6-bit here). It generated the best space invaders game I've seen yet for a local model (even included sound effects!). Generated 6600 tokens and ran at 16 tok/s.

GLM-4.7 runs quite well on an M3 Ultra with mlx-lm, even at a near lossless precision (6-bit here). It generated the best space invaders game I've seen yet for a local model (even included sound effects!). Generated 6600 tokens and ran at 16 tok/s.

Awni Hannun

237,191 次观看 • 7 个月前

Qwen 32B (4-bit) generates at >40 toks/sec on an M4 Max with assisted decoding and Qwen 0.5B as the draft model. Coming soon to mlx-lm. Compare regular decoding (left) to assisted decoding (right):

Qwen 32B (4-bit) generates at >40 toks/sec on an M4 Max with assisted decoding and Qwen 0.5B as the draft model. Coming soon to mlx-lm. Compare regular decoding (left) to assisted decoding (right):

Awni Hannun

50,353 次观看 • 1 年前

First results are in. Llama 4 Maverick 17B active / 400B total is blazing fast with MLX on an M3 Ultra. Here is the 4-bit model generating 1100 tokens at 50 tok/sec:

First results are in. Llama 4 Maverick 17B active / 400B total is blazing fast with MLX on an M3 Ultra. Here is the 4-bit model generating 1100 tokens at 50 tok/sec:

Awni Hannun

149,855 次观看 • 1 年前

Running Qwen2 VL 72B 4bit 🇨🇳 quantized model on Mac Mini M4 Pro 64GB. It works very well and delivers good accuracy, suitable for practical use cases. Integrating MLX and MLX-VLM backend into Sparrow as main solution for local inference and data extraction. Kudos to Prince Canuma for porting Qwen2 VL to MLX.

Running Qwen2 VL 72B 4bit 🇨🇳 quantized model on Mac Mini M4 Pro 64GB. It works very well and delivers good accuracy, suitable for practical use cases. Integrating MLX and MLX-VLM backend into Sparrow as main solution for local inference and data extraction. Kudos to Prince Canuma for porting Qwen2 VL to MLX.

Andrej Baranovskij

13,742 次观看 • 1 年前

The new Kimi K2 1T model (4-bit quant) runs on 2 512GB M3 Ultras with mlx-lm and mx.distributed. 1 trillion params, at a speed that's actually quite usable:

The new Kimi K2 1T model (4-bit quant) runs on 2 512GB M3 Ultras with mlx-lm and mx.distributed. 1 trillion params, at a speed that's actually quite usable:

Awni Hannun

238,152 次观看 • 1 年前

GLM 4.6 runs quite fast on an M3 Ultra with mlx-lm even at higher precision. Pretty remarkable that it benchmarks competitive to the just-released Sonnet 4.5. Hope those benchmarks hold-up in day-to-day use. Here's a run using 5.5 bpw quantized model, generating 5.3k tokens at 17+ tok/sec using 244 GB. What prompts should I test?

GLM 4.6 runs quite fast on an M3 Ultra with mlx-lm even at higher precision. Pretty remarkable that it benchmarks competitive to the just-released Sonnet 4.5. Hope those benchmarks hold-up in day-to-day use. Here's a run using 5.5 bpw quantized model, generating 5.3k tokens at 17+ tok/sec using 244 GB. What prompts should I test?

Awni Hannun

68,539 次观看 • 10 个月前

For even higher throughput and lower latency: batch generation + tensor parallel with mlx-lm + and mlx.distributed. Here it's generating at 63 tok/sec (throughput) with GLM 4.7 in 6-bit and batch size 4 on 4 M3 Ultras:

For even higher throughput and lower latency: batch generation + tensor parallel with mlx-lm + and mlx.distributed. Here it's generating at 63 tok/sec (throughput) with GLM 4.7 in 6-bit and batch size 4 on 4 M3 Ultras:

Awni Hannun

22,721 次观看 • 7 个月前

NVIDIA just released Nemotron 3 Ultra, a leading Hybrid Mamba-Transformer MoE open model for long-running agents. I've been test driving it these past few days, letting it work on Pi issues and it performed amazingly well! Update your and use it via OpenRouter today!

NVIDIA just released Nemotron 3 Ultra, a leading Hybrid Mamba-Transformer MoE open model for long-running agents. I've been test driving it these past few days, letting it work on Pi issues and it performed amazingly well! Update your and use it via OpenRouter today!

Mario Zechner

32,745 次观看 • 2 个月前

For a long time, local models were basically unusable in Cline. But these models are getting better & smaller 👀 model: lmstudio-community/Qwen3-30B-A3B-GGUF (3-bit, 14.58 GB) hardware: MacBook Pro (M4 Max, 36GB RAM) (run via LM Studio)

For a long time, local models were basically unusable in Cline. But these models are getting better & smaller 👀 model: lmstudio-community/Qwen3-30B-A3B-GGUF (3-bit, 14.58 GB) hardware: MacBook Pro (M4 Max, 36GB RAM) (run via LM Studio)

Cline

49,988 次观看 • 1 年前

Google's new Gemma 4 is excellent, and the 26B MoE version is likely the best model to run on a 32GB Framework Desktop. It's fast, smart, and also great for tool calling if you use it with OpenClaw🦞 or other local agent platforms.

Google's new Gemma 4 is excellent, and the 26B MoE version is likely the best model to run on a 32GB Framework Desktop. It's fast, smart, and also great for tool calling if you use it with OpenClaw🦞 or other local agent platforms.

Framework

58,593 次观看 • 4 个月前