All tasks / Tools
MLX-VLM
Python package to run and fine-tune vision-language models locally on Apple Silicon Macs with MLX.
- Blaizzy (open-source project)
- Local only
- Free, open source
Where it ranks
- AImage understandingRuntimes & gateways · Local · via Gemma 4 (31B)
Tools without a benchmark of their own inherit the tier of the best model they offer.
Facts
- Vendor
- Blaizzy (open-source project)
- Approach
- Runtimes & gateways
- Where it runs
- Runs only on your own hardware
- Interface
- Command line, API
- Skill level
- Advanced: command line, node graphs or self-hosting
- Price
- Free, open source
- Pricing notes
- Free and open source.
- Source code
- Open source (MIT)
- GitHub stars
- 5.6k (19 Oct 2026)
- Last verified
- 19 Oct 2026
Price from github.com, 19 Oct 2026.
Models it gives you
- AGemma 4 (31B)Google DeepMind · open weights
- AQwen3.8-27BAlibaba (Qwen) · open weights
- CMolmo2-8BAllen Institute for AI (Ai2) · open weights
- –Moondream 3.1 (9B-A2B)Moondream (M87 Labs) · open weights
- –MiniCPM-V 4.7 (35B-A3B)OpenBMB · open weights