Jan-v2-VL-med-4bit-mlx
mlx-community/Jan-v2-VL-med-4bit-mlx
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- janhq/Jan-v2-VL-med (quantized)
- Vendor
- janhq
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 41 in the last 30 days · 297 all time · 0 likes
- Published
- 2025-11-15 · updated 2026-02-12 (9mo ago)
- Languages
- en
- Tags
- qwen3_vl, vision, multimodal
Other MLX builds of janhq/Jan-v2-VL-med
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Jan-v2-VL-med-bf16-mlx | bf16 | ≈ 17.5 GB | 24 GB+ | 7 |
| Jan-v2-VL-med-4bit-mlx (this one) | 4-bit | — | — | 41 |
| Jan-v2-VL-med-8bit-mlx | 8-bit | — | — | 7 |