{"slug": "mlx-vlm", "name": "mlx-vlm", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 3, "commenters": 9, "warners": 0, "score": 4.354, "rising": -0.98, "first": "2025-12-06", "latest": "2026-10-27", "why": "", "why_is_quote": false, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 6, "compare": 0, "warn": 0}, "spark": [0, 1, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "", "kind": "", "icon": false, "domain": null, "github_repo": "github.com/blaizzy/mlx-vlm", "official_url": "https://github.com/Blaizzy/mlx-vlm", "pricing": "", "aliases": ["mlx-vlm", "MLX-VLM", "mlx_vlm"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 783755360, "item_id": 48984710, "url": "https://news.ycombinator.com/item?id=48984710", "by": "erikkahler", "date": "2026-07-20", "version": null, "stance": "recommend", "quote": "the popular MLX-VLM library", "excerpt": "To clarify, this MIT-licensed app is from the very same dev, 'Prince Canuma', who maintains the popular MLX-VLM library (https://github.com/Blaizzy/mlx-vlm). MLX-VLM is a long-time dependency of the excellent LM Studio and others because it can provide faster inference on Apple devices than llama.cpp. Historically, MLX is a smaller community than CUDA, but has some of the fastest updates upon the release of new model", "context": "", "use_case": "fast inference on Apple devices", "switched_from": "", "story": "Nativ: Run frontier open models locally on your Mac"}, {"id": 738864978, "item_id": 46179061, "url": "https://news.ycombinator.com/item?id=46179061", "by": "waybarrios", "date": "2025-12-06", "version": null, "stance": "recommend", "quote": "mlx-lm / mlx-vlm \u2014 great work by others", "excerpt": "Hey HN! I\u2019ve been experimenting with MLX (and mlx-lm / mlx-vlm \u2014 great work by others) and started a small WIP project to see how vLLM-style ideas could work on Apple Silicon. It\u2019s super early, just me tweaking things and learning, but if you\u2019re into MLX or running LLMs/VLMs on a Mac, I\u2019d love feedback or contributors. Repo: https://github.com/waybarrios/vllm-mlx", "context": "", "use_case": "", "switched_from": "", "story": "Trying VLLM Ideas on Apple Silicon with MLX (WIP)"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["running local models for agents", "vision-language inference", "running vision-language models", "fast inference on apple devices"], "compared": [{"slug": "llama-cpp", "name": "llama.cpp", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "mlx-lm", "name": "mlx-lm", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "lm-studio", "name": "LM Studio", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48982681", "title": "Nativ: Run frontier open models locally on your Mac", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=50262229", "title": "Introducing LFM3: Every Modality for Specialized Intelligence", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50011229", "title": "Ask HN: Got a Mac for running agents? what's your setup?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47863217", "title": "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47651540", "title": "Running Google Gemma 4 Locally with LM Studio's New Headless CLI and Claude Code", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47616361", "title": "Google releases Gemma 4 open models", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"recommend": 1}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"neutral": 3}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 2, "neutral": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {"neutral": 2}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 804239488, "item_id": 50264968, "url": "https://news.ycombinator.com/item?id=50264968", "by": "samstevens", "date": "2026-10-27", "version": null, "stance": "neutral", "quote": "I think mlx-vlm should support both the Audio and the Omni model", "excerpt": "I think mlx-vlm should support both the Audio and the Omni model: https://github.com/Blaizzy/mlx-vlm/ and there should be native MLX exports for both here: - https://huggingface.co/LiquidAI/LFM3-Audio-2B-MLX-8bit - https://huggingface.co/LiquidAI/LFM3-Omni-2B-MLX-8bit", "context": "", "use_case": "", "switched_from": "", "story": "Introducing LFM3: Every Modality for Specialized Intelligence"}, {"id": 800223041, "item_id": 50013940, "url": "https://news.ycombinator.com/item?id=50013940", "by": "umtksa", "date": "2026-10-08", "version": null, "stance": "neutral", "quote": "m2 24gb macbook mlx-lm & mlx-vlm own harness", "excerpt": "m2 24gb macbook mlx-lm & mlx-vlm own harness", "context": "", "use_case": "running local models for agents", "switched_from": "", "story": "Ask HN: Got a Mac for running agents? what's your setup?"}, {"id": 783798449, "item_id": 48987403, "url": "https://news.ycombinator.com/item?id=48987403", "by": "walrus01", "date": "2026-07-20", "version": null, "stance": "recommend", "quote": "", "excerpt": "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", "context": "", "use_case": "Vision-language inference", "switched_from": "", "story": "Nativ: Run frontier open models locally on your Mac"}, {"id": 783767714, "item_id": 48985482, "url": "https://news.ycombinator.com/item?id=48985482", "by": "jdiff", "date": "2026-07-20", "version": null, "stance": "neutral", "quote": "It automatically picked up the existing models I was using with mlx_vm directly", "excerpt": "I use oMLX and I'm tentatively going to be giving this a shot. oMLX keeps driving me up a wall with odd papercuts, bugs, and silent failures and fallbacks that are only visible buried deep inside logs when they should be announced out loud. The maintainer of mlx-vlm being behind this as well is the main thing kicking me over into trying it, even if it is incredibly young. I'm confused and unenthused to see it chompin", "context": "", "use_case": "running vision-language models", "switched_from": "", "story": "Nativ: Run frontier open models locally on your Mac"}, {"id": 783755360, "item_id": 48984710, "url": "https://news.ycombinator.com/item?id=48984710", "by": "erikkahler", "date": "2026-07-20", "version": null, "stance": "recommend", "quote": "the popular MLX-VLM library", "excerpt": "To clarify, this MIT-licensed app is from the very same dev, 'Prince Canuma', who maintains the popular MLX-VLM library (https://github.com/Blaizzy/mlx-vlm). MLX-VLM is a long-time dependency of the excellent LM Studio and others because it can provide faster inference on Apple devices than llama.cpp. Historically, MLX is a smaller community than CUDA, but has some of the fastest updates upon the release of new model", "context": "", "use_case": "fast inference on Apple devices", "switched_from": "", "story": "Nativ: Run frontier open models locally on your Mac"}, {"id": 767341168, "item_id": 47958823, "url": "https://news.ycombinator.com/item?id=47958823", "by": "danielhanchen", "date": "2026-04-29", "version": null, "stance": "neutral", "quote": "so it installs https://github.com/Blaizzy/mlx-vlm and other components", "excerpt": "Sorry on the delay - so it installs https://github.com/Blaizzy/mlx-vlm and other components and sets up the commands - you don't need to use it but we thought it might be easier for folks", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"}, {"id": 762569345, "item_id": 47660584, "url": "https://news.ycombinator.com/item?id=47660584", "by": "peder", "date": "2026-04-06", "version": null, "stance": "neutral", "quote": "I have been using mlx_vlm and vMLX", "excerpt": "Did you have any Anthropic vs OpenAI specification issues with Claude Code? I have been using mlx_vlm and vMLX and I get 400 Bad Request errors from Claude Code. Presumably you're not seeing those issues with llama-server ?", "context": "", "use_case": "", "switched_from": "", "story": "Running Google Gemma 4 Locally with LM Studio's New Headless CLI and Claude Code"}, {"id": 761919169, "item_id": 47619948, "url": "https://news.ycombinator.com/item?id=47619948", "by": "philipkglass", "date": "2026-04-02", "version": null, "stance": "neutral", "quote": "Use the mlx-vlm back end", "excerpt": "If you have a basic ARM MacBook, GLM-OCR is the best single model I have found for OCR over documents with good table extraction/formatting. It's a compact 0.9b parameter model, so it'll run on systems with only 8 GB of RAM. https://github.com/zai-org/GLM-OCR Use the mlx-vlm back end: https://github.com/zai-org/GLM-OCR/blob/main/examples/mlx-deploy/README.md Then you can run a single command to process your PDF: glmo", "context": "", "use_case": "", "switched_from": "", "story": "Google releases Gemma 4 open models"}, {"id": 738864978, "item_id": 46179061, "url": "https://news.ycombinator.com/item?id=46179061", "by": "waybarrios", "date": "2025-12-06", "version": null, "stance": "recommend", "quote": "mlx-lm / mlx-vlm \u2014 great work by others", "excerpt": "Hey HN! I\u2019ve been experimenting with MLX (and mlx-lm / mlx-vlm \u2014 great work by others) and started a small WIP project to see how vLLM-style ideas could work on Apple Silicon. It\u2019s super early, just me tweaking things and learning, but if you\u2019re into MLX or running LLMs/VLMs on a Mac, I\u2019d love feedback or contributors. Repo: https://github.com/waybarrios/vllm-mlx", "context": "", "use_case": "", "switched_from": "", "story": "Trying VLLM Ideas on Apple Silicon with MLX (WIP)"}]}