Falcon3-7B-Instruct-1.58bit-4bit
mlx-community/Falcon3-7B-Instruct-1.58bit-4bit
Text generation · mlx
58-bit Open on Hugging Face
Parameters
3.5B
Weights (est.)
≈ 3.8 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/Falcon3-7B-Instruct-1.58bit-4bit --prompt "Hello"
Details
- Base model
- tiiuae/Falcon3-7B-Instruct-1.58bit (quantized)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- 58-bit
- Licence
- falcon-llm-license
- Downloads
- 53 in the last 30 days · 330 all time · 1 likes
- Published
- 2025-06-10 · updated 2025-06-10 (1y ago)
- Tags
- llama, bitnet, falcon3
Other MLX builds of tiiuae/Falcon3-7B-Instruct-1.58bit
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon3-7B-Instruct-1.58bit-6bit | 58-bit | ≈ 2.3 GB | 8 GB+ | 30 |
| Falcon3-7B-Instruct-1.58bit-8bit | 58-bit | ≈ 2.5 GB | 8 GB+ | 31 |
| Falcon3-7B-Instruct-1.58bit | 58-bit | ≈ 3.3 GB | 8 GB+ | 39 |
| Falcon3-7B-Instruct-1.58bit-4bit (this one) | 58-bit | ≈ 3.8 GB | 8 GB+ | 53 |