Jan-v2-VL-low-bf16-mlx
mlx-community/Jan-v2-VL-low-bf16-mlx
Uncategorised · mlx
bf16 Open on Hugging Face
Parameters
8.8B
Weights (est.)
≈ 17.5 GB
Mac memory (est.)
24 GB+
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-low (finetune)
- Vendor
- janhq
- Task
- Uncategorised
- Quantisation
- bf16
- Licence
- apache-2.0
- Downloads
- 9 in the last 30 days · 92 all time · 0 likes
- Published
- 2025-11-15 · updated 2025-11-15 (1y ago)
- Languages
- en
- Tags
- qwen3_vl, vision, multimodal
Other MLX builds of janhq/Jan-v2-VL-low
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Jan-v2-VL-low-bf16-mlx (this one) | bf16 | ≈ 17.5 GB | 24 GB+ | 9 |
| Jan-v2-VL-low-4bit-mlx | 4-bit | — | — | 28 |
| Jan-v2-VL-low-8bit-mlx | 8-bit | — | — | 13 |