Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Qwen 3.5 397B prompt processing on M3 Ultra (with MLX distributed + JACCL) - 3.4× speedup on 4 chips - scaling improves as context increases Really fun to use with opencode; generated a playable Asteroids clone in ~4 minutes (real time, including me playing it a bit).

angeloskath's profile picture

Angelos Katharopoulos

4,551 subscribers

23,348 Aufrufe • vor 3 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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:
0:50

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

186,641 Aufrufe • vor 10 Monaten

MiniMax M2.1 in 4-bit cruises on an M3 Ultra with mlx-lm. Generated a space invaders game using 5098 tokens at 47.2 tok/sec:
0:23

MiniMax M2.1 in 4-bit cruises on an M3 Ultra with mlx-lm. Generated a space invaders game using 5098 tokens at 47.2 tok/sec:

Awni Hannun

93,826 Aufrufe • vor 5 Monaten

A long time coming but new mlx-lm is here with better batching support in the server and Gemma 4. pip install -U mlx-lm Here is a video where a single M3 Ultra serves 5 opencode sessions with Gemma 4 26B that process ~130k tokens in ~1.5 minutes.
2:03

A long time coming but new mlx-lm is here with better batching support in the server and Gemma 4. pip install -U mlx-lm Here is a video where a single M3 Ultra serves 5 opencode sessions with Gemma 4 26B that process ~130k tokens in ~1.5 minutes.

Angelos Katharopoulos

66,089 Aufrufe • vor 2 Monaten

Step-3.5-Flash in action on MLX with OpenCode on a single (distributed testing in progress!) M3 Ultra to create a snake game! 🔥 6bit quantization. Perfect tool calling. Fast & powerful coding model! Recommended Inference Settings: Temperature: 1.0 Top-p: 0.95 Top-k: 40 🧵
0:27

Step-3.5-Flash in action on MLX with OpenCode on a single (distributed testing in progress!) M3 Ultra to create a snake game! 🔥 6bit quantization. Perfect tool calling. Fast & powerful coding model! Recommended Inference Settings: Temperature: 1.0 Top-p: 0.95 Top-k: 40 🧵

Ivan Fioravanti ᯅ

17,158 Aufrufe • vor 4 Monaten

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:
0:44

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 Aufrufe • vor 1 Jahr

The new Deep Seek V3 0324 in 4-bit runs at > 20 toks/sec on a 512GB M3 Ultra with mlx-lm!
0:31

The new Deep Seek V3 0324 in 4-bit runs at > 20 toks/sec on a 512GB M3 Ultra with mlx-lm!

Awni Hannun

168,841 Aufrufe • vor 1 Jahr

Qwen3.5-397B-A17B with Vision running on a Single M3 Ultra 🚀 Shout out to the Qwen team because they cooked with this model! Get started today: > uv pip install -U mlx-vlm Model collection 👇🏽 Repo:
0:59

Qwen3.5-397B-A17B with Vision running on a Single M3 Ultra 🚀 Shout out to the Qwen team because they cooked with this model! Get started today: > uv pip install -U mlx-vlm Model collection 👇🏽 Repo:

Prince Canuma

11,386 Aufrufe • vor 3 Monaten

MLX + OpenCode + Qwen3.5-122B-A10B-4bit on M3 Ultra created a great snake game! Work zero-shot. Video clearly in super fast mode during generation. I generated the prompt using Grok 4.20, it's in the article.
0:21

MLX + OpenCode + Qwen3.5-122B-A10B-4bit on M3 Ultra created a great snake game! Work zero-shot. Video clearly in super fast mode during generation. I generated the prompt using Grok 4.20, it's in the article.

Ivan Fioravanti ᯅ

74,659 Aufrufe • vor 3 Monaten

The new Qwen 3.5 by Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon.
0:25

The new Qwen 3.5 by Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon.

Adrien Grondin

3,552,278 Aufrufe • vor 3 Monaten

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:
0:20

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

149,847 Aufrufe • vor 1 Jahr

Having some fun with the new speculative generation feature in LM Studio: -MLX 4-bit Qwen 32B/0.5B draft runs a lot faster for coding tasks than the 32B model alone -Nice to visualizase the draft tokens generated:
0:25

Having some fun with the new speculative generation feature in LM Studio: -MLX 4-bit Qwen 32B/0.5B draft runs a lot faster for coding tasks than the 32B model alone -Nice to visualizase the draft tokens generated:

Awni Hannun

12,642 Aufrufe • vor 1 Jahr

Running Minimax M2.1 (MiniMax (official)) with OpenCode (OpenCode) and mlx_lm.server. Works quite well on an M3 Ultra. Once the KV cache is warm the prompt processing is pretty quick. And token generation is very fast.
0:41

Running Minimax M2.1 (MiniMax (official)) with OpenCode (OpenCode) and mlx_lm.server. Works quite well on an M3 Ultra. Once the KV cache is warm the prompt processing is pretty quick. And token generation is very fast.

Awni Hannun

32,329 Aufrufe • vor 5 Monaten

Running Ring 1T reasoning model on a single M3 Ultra with mlx-lm. It's quantized to 3.5 bits-per-weight. Uses 440GB and generated ~6k tokens at 18.2 toks/sec. Getting closer to GPT-5 at home.
0:59

Running Ring 1T reasoning model on a single M3 Ultra with mlx-lm. It's quantized to 3.5 bits-per-weight. Uses 440GB and generated ~6k tokens at 18.2 toks/sec. Getting closer to GPT-5 at home.

Awni Hannun

55,131 Aufrufe • vor 8 Monaten

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:
0:29

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

51,029 Aufrufe • vor 6 Monaten

Qwen3 235B MoE (22B active) runs so fast on an M2 Ultra with mlx-lm. - 4-bit model uses ~132GB - Generated 580 tokens at ~28 toks/sec
0:29

Qwen3 235B MoE (22B active) runs so fast on an M2 Ultra with mlx-lm. - 4-bit model uses ~132GB - Generated 580 tokens at ~28 toks/sec

Awni Hannun

117,763 Aufrufe • vor 1 Jahr

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):
0:23

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 Aufrufe • vor 1 Jahr

🎊 Kudos to the teams at Qwen on the launch of Qwen 3.5 with Qwen3.5-397B-A17B. 🙌 Developers can start building today for free: Or download and customize it with NVIDIA NeMo:
0:49

🎊 Kudos to the teams at Qwen on the launch of Qwen 3.5 with Qwen3.5-397B-A17B. 🙌 Developers can start building today for free: Or download and customize it with NVIDIA NeMo:

NVIDIA AI Developer

26,904 Aufrufe • vor 4 Monaten

Just for fun, here's what 32 simultaneous long-context generations with Qwen3 Next 80B looks like on an M3 Ultra. Using the new batch generation in mlx-lm. Context size for each is about 5k tokens:
0:41

Just for fun, here's what 32 simultaneous long-context generations with Qwen3 Next 80B looks like on an M3 Ultra. Using the new batch generation in mlx-lm. Context size for each is about 5k tokens:

Awni Hannun

50,272 Aufrufe • vor 8 Monaten

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.
0:53

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

233,002 Aufrufe • vor 5 Monaten

DeepSeek-R1-0528-5bit on MLX pushing M3 Ultra 512GB to its limits! 501GB used mem visibile on mactop in the video! Context: 4K tokens Prompt: 190.29 t/s Gen: 11.37 t/s Peak Mem: 487.48 GB! THIS IS APPLE MLX!
0:20

DeepSeek-R1-0528-5bit on MLX pushing M3 Ultra 512GB to its limits! 501GB used mem visibile on mactop in the video! Context: 4K tokens Prompt: 190.29 t/s Gen: 11.37 t/s Peak Mem: 487.48 GB! THIS IS APPLE MLX!

Ivan Fioravanti ᯅ

102,949 Aufrufe • vor 11 Monaten