mlx-vlm
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
0warn against
Dec 6, 2025first mention
Oct 27, 2026latest mention
Why people recommend it
“the popular MLX-VLM library”
“mlx-lm / mlx-vlm — great work by others”
Caveats and dissent
No one in these comments warned against it.
Often compared with
Threads where it came up
- Nativ: Run frontier open models locally on your Mac 3 mentions
- Introducing LFM3: Every Modality for Specialized Intelligence 1 mention
- Ask HN: Got a Mac for running agents? what's your setup? 1 mention
- Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model 1 mention
- Running Google Gemma 4 Locally with LM Studio's New Headless CLI and Claude Code 1 mention
- Google releases Gemma 4 open models 1 mention
Also written as MLX-VLM, mlx_vlm. Data: mlx-vlm.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 9
“I think mlx-vlm should support both the Audio and the Omni model”
“m2 24gb macbook mlx-lm & mlx-vlm own harness”
I would also note that for people who want to download these models, you can find MLX versions of just about everything popular on huggingface these days. For instance go look at the "main" page for Qwen 3.6 35B-A3B and then follow the link to quantizations, and pick one of the more popular/reputable MLX variants. https://huggingface.co/Qwen/Qwen3.6-35B-A3B
“It automatically picked up the existing models I was using with mlx_vm directly”
“the popular MLX-VLM library”
“so it installs https://github.com/Blaizzy/mlx-vlm and other components”
“I have been using mlx_vlm and vMLX”
“Use the mlx-vlm back end”
“mlx-lm / mlx-vlm — great work by others”