4-bit Open on Hugging Face
Parameters
7.5B
Weights (est.)
≈ 4.2 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/Falcon3 --prompt "Hello"
Details
- Base model
- tiiuae/Falcon3-7B-Instruct (quantized)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- falcon-llm-license
- Downloads
- 34 in the last 30 days · 303 all time · 0 likes
- Published
- 2024-12-17 · updated 2024-12-17 (1y ago)
- Languages
- en, fr, es, pt
- Tags
- llama, falcon3
Other MLX builds of tiiuae/Falcon3-7B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon3-7B-Instruct-3bit | 3-bit | ≈ 3.3 GB | 8 GB+ | 27 |
| Falcon3-7B-Instruct-4bit | 4-bit | ≈ 4.2 GB | 8 GB+ | 619 |
| Falcon3 (this one) | 4-bit | ≈ 4.2 GB | 8 GB+ | 34 |
| Falcon3-7B-Instruct-6bit | 6-bit | ≈ 6.1 GB | 16 GB+ | 43 |
| Falcon3-7B-Instruct-8bit | 8-bit | ≈ 7.9 GB | 16 GB+ | 32 |