Parameters
793M
Weights (est.)
≈ 3.2 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/mamba-790m-hf-f32 --prompt "Hello"
Details
- Base model
- state-spaces/mamba-790m-hf (finetune)
- Vendor
- state-spaces
- Task
- Text generation
- Quantisation
- Not stated
- Licence
- —
- Downloads
- 19 in the last 30 days · 400 all time · 0 likes
- Published
- 2024-09-21 · updated 2024-09-21 (2y ago)
- Tags
- mamba
Other MLX builds of state-spaces/mamba-790m-hf
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| mamba-790m-hf-f16 | — | ≈ 1.6 GB | 8 GB+ | 17 |
| mamba-790m-hf-f32 (this one) | — | ≈ 3.2 GB | 8 GB+ | 19 |