bf16 Open on Hugging Face
Parameters
4.0B
Weights (est.)
≈ 8.0 GB
Mac memory (est.)
16 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Jan-nano-4B-bf16 --prompt "Hello"
Details
- Base model
- Menlo/Jan-nano (finetune)
- Vendor
- Menlo
- Task
- Text generation
- Quantisation
- bf16
- Licence
- apache-2.0
- Downloads
- 41 in the last 30 days · 422 all time · 0 likes
- Published
- 2025-07-05 · updated 2025-07-05 (1y ago)
- Tags
- qwen3
Other MLX builds of Menlo/Jan-nano
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Jan-nano-8bit | 8-bit | ≈ 4.3 GB | 8 GB+ | 64 |
| Jan-nano-4B-bf16 (this one) | bf16 | ≈ 8.0 GB | 16 GB+ | 41 |