Falcon3-Mamba-7B-Instruct-4bits
mlx-community/Falcon3-Mamba-7B-Instruct-4bits
Text generation · transformers
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/Falcon3-Mamba-7B-Instruct-4bits --prompt "Hello"
Details
- Base model
- tiiuae/Falcon3-Mamba-7B-Instruct (quantized)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- falcon-llm-license
- Downloads
- 48 in the last 30 days · 632 all time · 0 likes
- Published
- 2024-12-18 · updated 2025-02-14 (1y ago)
- Languages
- en
- Tags
- falcon_mamba, falcon3, falcon3_mamba
Other MLX builds of tiiuae/Falcon3-Mamba-7B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon3-Mamba-7B-Instruct-4bits (this one) | 4-bit | ≈ 4.1 GB | 8 GB+ | 48 |
| Falcon3-Mamba-7B-Instruct-8bits | 8-bit | ≈ 7.7 GB | 16 GB+ | 57 |
| Falcon3-Mamba-7B-Instruct | — | ≈ 14.5 GB | 24 GB+ | 38 |