janhq · First MLX build 15 Nov 2025
Jan-v2-VL-med
MLX
apache-2.0
A 8.8B parameter model from janhq, with 3 MLX builds, from bf16 to 8-bit.
- Parameters
- 8.8B From Hugging Face
- Quantisation
- 4-bit Jan-v2-VL-med-4bit-mlx
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 39 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Jan-v2-VL-med-4bit-mlxMLX builds
3 on mlx-community| Jan-v2-VL-med-bf16-mlx | bf16 | 17.5 GB | 22 GB | 7 |
|---|---|---|---|---|
| Jan-v2-VL-med-4bit-mlx | 4-bit | — | — | 39 |
| Jan-v2-VL-med-8bit-mlx | 8-bit | — | — | 7 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.