mlx-vlm
Shares rank 26 of 27 inference engines by recommenders
Runs vision-language models on Apple silicon with MLX and is said to infer faster than llama.cpp on Apple devices. Critics report bugs and weak support for modern samplers.
Runs vision-language models on Apple silicon with MLX and is said to infer faster than llama.cpp on Apple devices. Critics report bugs and weak support for modern samplers.
7 people gave an opinion
- recommend it
- 5
- criticize it
- 2
- approval share
- 71%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 5 people recommend itNeeds 10 or more, not met.
- 2.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Faster inference on Apple devices
“it can provide faster inference on Apple devices than llama.cpp”
Comment from 20 Jul 2026 in “Nativ: Run frontier open models locally on your Mac” Supports min-p sampling
“TBF mlx-vlm does support min-p sampling, but none of the other modern samplers that you list.”
Comment from 21 Jul 2026 in “Nativ: Run frontier open models locally on your Mac” Recently updated by maintainer
“Prince Canuma just updated mlx-vlm”
Comment from 3 Apr 2026 in “Google releases Gemma 4 open models”
What people warn about
Each mark is one comment
Weak support for modern samplers
“Switching to mlx-vlm is basically harmful since it (like vllm and sglang) have such garbage support for modern samplers.”
Comment from 21 Jul 2026 in “Nativ: Run frontier open models locally on your Mac” “TBF mlx-vlm does support min-p sampling, but none of the other modern samplers that you list.”
Comment from 21 Jul 2026 in “Nativ: Run frontier open models locally on your Mac” Many bugs, not official
“that is not official and has tons of bugs”
Comment from 8 Mar 2026 in “Lil Finder Guy”
Other inference engines people recommend
The four most recommended other inference engines, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| vLLM | 112 | 56 | 67% | 12 | — | Approved |
| Strata | 31 | 15 | 67% | 5 | — | Approved |
| DwarfStar 4 | 26 | 2 | 93% | 6 | — | Approved |
| SGLang | 19 | 13 | 59% | 8 | — | — |
| mlx-vlmThis page | 5 | 2 | 71% | 3 | — | — |
What people said
5 of the 7 comments that mention it, newest first. Each links to the original comment.
“TBF mlx-vlm does support min-p sampling, but none of the other modern samplers that you list.”
“Switching to mlx-vlm is basically harmful since it (like vllm and sglang) have such garbage support for modern samplers.”
“it can provide faster inference on Apple devices than llama.cpp”
“Prince Canuma just updated mlx-vlm”
“that is not official and has tons of bugs”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.