Loading video...

Video Failed to Load

Go Home

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 🧵

ivanfioravanti's profile picture

Ivan Fioravanti ᯅ

21,669 subscribers

17,158 views • 4 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

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 views • 10 months ago

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 views • 3 months ago

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).
4:13

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).

Angelos Katharopoulos

23,273 views • 2 months ago

OpenCode + GLM-4.7-Flash 8bit. llama-server vs mlx_lm.server. Using one M3 Ultra for each host. Same prompts, you can check duration for each step in the video. Amazing experience on both side! Local coding AI model are becoming reality! 🔥
2:21

OpenCode + GLM-4.7-Flash 8bit. llama-server vs mlx_lm.server. Using one M3 Ultra for each host. Same prompts, you can check duration for each step in the video. Amazing experience on both side! Local coding AI model are becoming reality! 🔥

Ivan Fioravanti ᯅ

47,063 views • 4 months ago

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

55,123 views • 8 months ago

GLM-5 runs with mlx-lm on a single 512GB M3 Ultra in Q4. It's quite good in my initial testing and pretty fast as well. It generated a highly functional space invaders game using 7.1k tokens at 15.4 tok/s and 419GB memory. Thanks to Gökdeniz Gülmez and Tarjei Mandt for the port.
1:11

GLM-5 runs with mlx-lm on a single 512GB M3 Ultra in Q4. It's quite good in my initial testing and pretty fast as well. It generated a highly functional space invaders game using 7.1k tokens at 15.4 tok/s and 419GB memory. Thanks to Gökdeniz Gülmez and Tarjei Mandt for the port.

Awni Hannun

60,446 views • 3 months ago

oMLX is working really well as single machine inference engine for coding agents! Caching is managed perfectly (it can use a ton of disk space, be aware!) and oQ quantization delivers great results. Behind the scenes it uses the standard MLX building blocks (75% created by Prince Canuma 🙏): - mlx-lm - mlx-vlm - mlx-embeddings - mlx-audio I tested Qwen3.6-35B-A3B-oQ6 on M5 Max with two pi instances and it was fast and furious and leveraging cache like crazy as you can see in the video. Let me try to create some oQ versions (2,4,6?) of MiniMax M2.7 now and then I'll pass to distributed inference. I must win! 💪
3:57

oMLX is working really well as single machine inference engine for coding agents! Caching is managed perfectly (it can use a ton of disk space, be aware!) and oQ quantization delivers great results. Behind the scenes it uses the standard MLX building blocks (75% created by Prince Canuma 🙏): - mlx-lm - mlx-vlm - mlx-embeddings - mlx-audio I tested Qwen3.6-35B-A3B-oQ6 on M5 Max with two pi instances and it was fast and furious and leveraging cache like crazy as you can see in the video. Let me try to create some oQ versions (2,4,6?) of MiniMax M2.7 now and then I'll pass to distributed inference. I must win! 💪

Ivan Fioravanti ᯅ

19,258 views • 1 month ago

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

65,949 views • 1 month ago

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 views • 5 months ago

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 views • 3 months ago

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.
0:28

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

46,577 views • 3 months ago

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

149,495 views • 1 year ago

GLM-4.7-8bit (350GB) running at 19 toks/s on two M3 Ultra 512GB using Tensor Parallelism with EXO - MLX, versus 14 toks/s with single node. 🚀 Now context benchmarking & then OpenCode tests 🔥 Note: this is from sources, I had to change things to run it.
0:50

GLM-4.7-8bit (350GB) running at 19 toks/s on two M3 Ultra 512GB using Tensor Parallelism with EXO - MLX, versus 14 toks/s with single node. 🚀 Now context benchmarking & then OpenCode tests 🔥 Note: this is from sources, I had to change things to run it.

Ivan Fioravanti ᯅ

327,687 views • 5 months ago

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

168,815 views • 1 year ago

Gemini 3 Flash is fully available now on Orchids! Google's newest model - incredibly fast and powerful. Pixel perfect clone of X in under a minute.
0:25

Gemini 3 Flash is fully available now on Orchids! Google's newest model - incredibly fast and powerful. Pixel perfect clone of X in under a minute.

Bud

27,651 views • 5 months ago

🚨 Gemini 3.5 Flash built a full Ubuntu/GNOME web OS in ONE shot. single HTML file, embedded CSS + JS. from one prompt: >working dock + top bar >functional terminal & Game >file manager with real navigation >window drag, resize, minimize on every window >settings panel >boot animation prompt + full code in the reply 👇
2:27

🚨 Gemini 3.5 Flash built a full Ubuntu/GNOME web OS in ONE shot. single HTML file, embedded CSS + JS. from one prompt: >working dock + top bar >functional terminal & Game >file manager with real navigation >window drag, resize, minimize on every window >settings panel >boot animation prompt + full code in the reply 👇

Chetaslua

57,931 views • 19 days ago

Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)
4:07

Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)

Prince Canuma

123,478 views • 1 year ago

From back to front in a flash! A lightning fast counter-attack puts Portland Timbers back on top. ⚡
1:28

From back to front in a flash! A lightning fast counter-attack puts Portland Timbers back on top. ⚡

Major League Soccer

36,081 views • 1 year ago

I did it! It works! Using GLM-4.7-4bit with mlx_lm.server and opencode to fix real code locally! 🔥 Here single M3 Ultra 512GB, nex step phase will be 2 using Tensor Parallelism and then apply same changes to exo. Prefill is slow on a single machine, but generation is good.
1:44

I did it! It works! Using GLM-4.7-4bit with mlx_lm.server and opencode to fix real code locally! 🔥 Here single M3 Ultra 512GB, nex step phase will be 2 using Tensor Parallelism and then apply same changes to exo. Prefill is slow on a single machine, but generation is good.

Ivan Fioravanti ᯅ

44,000 views • 5 months ago

The new Qwen 3.5 4B runs incredibly well on M5. The model is close to GPT-4o in benchmarks. Running fully on-device with MLX.
0:20

The new Qwen 3.5 4B runs incredibly well on M5. The model is close to GPT-4o in benchmarks. Running fully on-device with MLX.

Adrien Grondin

230,124 views • 2 months ago