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。

Running four simultaneous OpenCode agents works well with mlx_lm.server continuous batching and MiniMax M2.1 on an M3 Ultra:

Awni Hannun

44,794 subscribers

95,013 次观看 • 5 个月前 •via X (Twitter)

新闻政治健康养生

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

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.

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 次观看 • 5 个月前

Running four high-level OpenCode agents + subagents with mlx_lm.server continuous batching and MiniMax M2.5 (6-bit). Fits easily on a 512GB M3 Ultra. Generation is quite fast. But prefill is still slow compared to cloud servers.

Running four high-level OpenCode agents + subagents with mlx_lm.server continuous batching and MiniMax M2.5 (6-bit). Fits easily on a 512GB M3 Ultra. Generation is quite fast. But prefill is still slow compared to cloud servers.

Awni Hannun

25,535 次观看 • 4 个月前

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:

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 次观看 • 5 个月前

I wasn't expecting such an intelligence model on my local machine. Minimax 2.1 on MLX🔥 git clone cd mlx-lm && pip install -e . mlx_lm.server --model mlx-community/MiniMax-M2.1-4bit

I wasn't expecting such an intelligence model on my local machine. Minimax 2.1 on MLX🔥 git clone cd mlx-lm && pip install -e . mlx_lm.server --model mlx-community/MiniMax-M2.1-4bit

mzba

30,377 次观看 • 5 个月前

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.

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 次观看 • 5 个月前

MiniMax M3 support added to mlx-vlm with MSA implementation! 🚀 Tested on M3 Ultra 512GB running at 24 tps with peak memory ~240GB. Now working on optimizing performance and adding ton of tests 💪 Model is here: PR is here:

MiniMax M3 support added to mlx-vlm with MSA implementation! 🚀 Tested on M3 Ultra 512GB running at 24 tps with peak memory ~240GB. Now working on optimizing performance and adding ton of tests 💪 Model is here: PR is here:

Ivan Fioravanti ᯅ

23,587 次观看 • 2 天前

This is MiniMax-M2.5 MLX running in LM Studio on an Apple Mac Studio M3 Ultra 512GB. Fast enough out of the box for hosting OpenClaw, n8n workflows, and Open WebUI for the team.

This is MiniMax-M2.5 MLX running in LM Studio on an Apple Mac Studio M3 Ultra 512GB. Fast enough out of the box for hosting OpenClaw, n8n workflows, and Open WebUI for the team.

Patrick J Kennedy

73,547 次观看 • 4 个月前

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! 🔥

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 次观看 • 4 个月前

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.

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 次观看 • 2 个月前

Next mlx-vlm release will ship with continuous batching support on the server 🚀 What's coming: → Continuous batching — new requests join the active batch immediately, no waiting. Mixed image + text batches supported → OpenAI-compatible API — field-for-field match with mlx-lm, reasoning/content split for thinking models, tag-aware streaming → Multi-turn tool calling — full tool use support across streaming and non-streaming, works with Gemma4 and other templates → Vision feature caching — cache image embeddings across turns. Gemma4: 228x speedup, Qwen3.5: 23x on cache hit All running locally on Apple Silicon. Check our this demo running 4 concurrent requests (mixed image + text) to gemma-4-26B-A4B-IT by Google Gemma in bf16 using Pi + MLX-VLM server on my M3 Ultra. One of the requests ingests a 8K resolution image!

Next mlx-vlm release will ship with continuous batching support on the server 🚀 What's coming: → Continuous batching — new requests join the active batch immediately, no waiting. Mixed image + text batches supported → OpenAI-compatible API — field-for-field match with mlx-lm, reasoning/content split for thinking models, tag-aware streaming → Multi-turn tool calling — full tool use support across streaming and non-streaming, works with Gemma4 and other templates → Vision feature caching — cache image embeddings across turns. Gemma4: 228x speedup, Qwen3.5: 23x on cache hit All running locally on Apple Silicon. Check our this demo running 4 concurrent requests (mixed image + text) to gemma-4-26B-A4B-IT by Google Gemma in bf16 using Pi + MLX-VLM server on my M3 Ultra. One of the requests ingests a 8K resolution image!

Prince Canuma

82,085 次观看 • 2 个月前

Notion Lite, one-shot by M2.1 on MiniMax Agent ✨ Fully playable:

Notion Lite, one-shot by M2.1 on MiniMax Agent ✨ Fully playable:

Skyler Miao

14,918 次观看 • 5 个月前

MiniMax M2.1 vs Opus 4.5 vs GLM-4.7 built an interactive 3D solar system from scratch. Running on 3 Claude Code in parallel. The winner is: 🥇 GLM-4.7! 🥈 Opus 4.5 (slowest) 🥉 M2.1 (fastest) GLM-4.7 design capabilities are another level vs 4.6!

MiniMax M2.1 vs Opus 4.5 vs GLM-4.7 built an interactive 3D solar system from scratch. Running on 3 Claude Code in parallel. The winner is: 🥇 GLM-4.7! 🥈 Opus 4.5 (slowest) 🥉 M2.1 (fastest) GLM-4.7 design capabilities are another level vs 4.6!

Ivan Fioravanti ᯅ

81,630 次观看 • 5 个月前

INCREDIBLE SPEED running Claude Code w/ local models on my own GPUs at home > SGLang serving MiniMax-M2.1 > on 8x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-2-end on my AI cluster MiniMax-M2.1 is my favorite model to run locally nowadays

INCREDIBLE SPEED running Claude Code w/ local models on my own GPUs at home > SGLang serving MiniMax-M2.1 > on 8x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-2-end on my AI cluster MiniMax-M2.1 is my favorite model to run locally nowadays

Ahmad

592,866 次观看 • 4 个月前

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

186,641 次观看 • 10 个月前

We ran the same prompt and identical starting context on MiniMax-M2.1 and Claude Sonnet 4.5. MiniMax-M2.1 by MiniMax (official) reached a usable result faster, required fewer structural fixes, and produced a more consistent visual and interaction flow from the first pass. To test this properly, we asked both models to build a complex single-page web animation with real-world visual and physics constraints. Comparison video below 👇

We ran the same prompt and identical starting context on MiniMax-M2.1 and Claude Sonnet 4.5. MiniMax-M2.1 by MiniMax (official) reached a usable result faster, required fewer structural fixes, and produced a more consistent visual and interaction flow from the first pass. To test this properly, we asked both models to build a complex single-page web animation with real-world visual and physics constraints. Comparison video below 👇

GitHub Projects Community

29,252 次观看 • 5 个月前

You can use a 100% open source and MUCH cheaper/free alternative to Claude Code and Opus 4.5 OpenCode + MiniMax M2.1 can even build a 3D website using pure vibe coding. Steps are really simple: 1. Install OpenCode using the command 'npm i -g opencode-ai' 2. Get your MiniMax API key here: 3. Configure the MiniMax (official) mode Just type "opencode connect minimax" Coding plans start at $2… 10x cheaper than Claude Code (yes). You can also invite friends so they can get 10% off and you’ll get 10% API credits. (You can also use it locally if you have the config) And you're ready to build and iterate almost endlessly since the model is both way faster and cheaper than Opus in CC.

You can use a 100% open source and MUCH cheaper/free alternative to Claude Code and Opus 4.5 OpenCode + MiniMax M2.1 can even build a 3D website using pure vibe coding. Steps are really simple: 1. Install OpenCode using the command 'npm i -g opencode-ai' 2. Get your MiniMax API key here: 3. Configure the MiniMax (official) mode Just type "opencode connect minimax" Coding plans start at $2… 10x cheaper than Claude Code (yes). You can also invite friends so they can get 10% off and you’ll get 10% API credits. (You can also use it locally if you have the config) And you're ready to build and iterate almost endlessly since the model is both way faster and cheaper than Opus in CC.

Paul Couvert

42,443 次观看 • 5 个月前

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.

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 次观看 • 5 个月前

i built an ipod inspired yt music desktop client using MiniMax (official) and opencode in 1 night 100% rust. check it out

i built an ipod inspired yt music desktop client using MiniMax (official) and opencode in 1 night 100% rust. check it out

shydev

15,971 次观看 • 4 个月前

🔥DeepSeek-v3-0324-8bit (~700GB) running on 2 x M3 Ultra 512GB ~12 tokens/sec Here the video!

🔥DeepSeek-v3-0324-8bit (~700GB) running on 2 x M3 Ultra 512GB ~12 tokens/sec Here the video!

Ivan Fioravanti ᯅ

19,761 次观看 • 1 年前

Yo LinkedIn, idk why you are paying $100k to developers i just rebuilt it with a single prompt using MiniMax M2.1 with BLACKBOX AI

Yo LinkedIn, idk why you are paying $100k to developers i just rebuilt it with a single prompt using MiniMax M2.1 with BLACKBOX AI

Karthik

426,081 次观看 • 5 个月前