4-bit Open on Hugging Face
Parameters
1.7B
Weights (est.)
≈ 968 MB
Mac memory (est.)
8 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-v1-edge-4bit --prompt "Hello"
Details
- Base model
- janhq/Jan-v1-edge (quantized)
- Vendor
- janhq
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 38 in the last 30 days · 364 all time · 1 likes
- Published
- 2025-09-04 · updated 2025-09-04 (1y ago)
- Languages
- en
- Tags
- qwen3
Other MLX builds of janhq/Jan-v1-edge
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Jan-v1-edge-4bit (this one) | 4-bit | ≈ 968 MB | 8 GB+ | 38 |
| Jan-v1-edge-8bit | 8-bit | ≈ 1.8 GB | 8 GB+ | 28 |
| Jan-v1-edge-bf16 | bf16 | ≈ 3.4 GB | 8 GB+ | 29 |