4-bit Open on Hugging Face
Parameters
7.3B
Weights (est.)
≈ 4.1 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/falcon-mamba-7b-4bit-instruct --prompt "Hello"
Details
- Base model
- tiiuae/falcon-mamba-7b-instruct (quantized)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- falcon-mamba-7b-license
- Downloads
- 40 in the last 30 days · 452 all time · 0 likes
- Published
- 2024-11-15 · updated 2024-11-15 (2y ago)
- Languages
- en
- Tags
- falcon_mamba
Other MLX builds of tiiuae/falcon-mamba-7b-instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| falcon-mamba-7b-4bit-instruct (this one) | 4-bit | ≈ 4.1 GB | 8 GB+ | 40 |
| falcon-mamba-7b-8bit-instruct | 8-bit | ≈ 7.7 GB | 16 GB+ | 42 |