4-bit Open on Hugging Face
Parameters
3.0B
Weights (est.)
≈ 1.7 GB
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/AI21-Jamba-Reasoning-3B-4bit --prompt "Hello"
Details
- Base model
- ai21labs/AI21-Jamba-Reasoning-3B (quantized)
- Vendor
- AI21 · Jamba
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 186 in the last 30 days · 1.3K all time · 1 likes
- Published
- 2025-10-14 · updated 2025-10-14 (1y ago)
- Tags
- jamba
Other MLX builds of ai21labs/AI21-Jamba-Reasoning-3B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| AI21-Jamba-Reasoning-3B-4bit (this one) | 4-bit | ≈ 1.7 GB | 8 GB+ | 186 |
| AI21-Jamba-Reasoning-3B-6bit | 6-bit | ≈ 2.5 GB | 8 GB+ | 50 |
| AI21-Jamba-Reasoning-3B-bf16 | bf16 | ≈ 6.1 GB | 16 GB+ | 65 |