MLX-VLM v0.7.12
Adds Mistral Large 4, Raon-1 Mini, Mage-VL-Cowork support, speculative thinking budgets, and reasoning-effort control.
The Deploy Log | Products | Free, no signup
5 versions of MLX-VLM from MLX-VLM in The Deploy Log. From to . On the median a new version every 10 days, publisher's dates only; the longest wait was 15 days. The newest is v0.7.12. 3 versions in the last 30 days. Each links the publisher's own page.
| Version | Publisher's date | Days after the one before |
|---|---|---|
| v0.7.12 | 14 | |
| v0.7.10 | 2 | |
| v0.7.9 | 6 | |
| v0.7.8 | 15 | |
| v0.7.4 |
Adds Mistral Large 4, Raon-1 Mini, Mage-VL-Cowork support, speculative thinking budgets, and reasoning-effort control.
MLX-VLM v0.7.10 adds Muse Spark Open support with audio/video/images and native Flint BF16 support.
MLX-VLM v0.7.9 adds Nemotron 3.5 Super VL support, live image resolution controls, and several vision model fixes.
MLX-VLM v0.7.8 adds Kolibri1 and EmbeddingGemma 2 multimodal embedding support.
Generate multiple images per prompt via num_images for qwen_image, flux2, ideogram4, plus audio and padding fixes.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.