8-bit Open on Hugging Face
Parameters
521M
Weights (est.)
≈ 554 MB
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-H1-0.5B-Instruct-8bit --prompt "Hello"
Details
- Base model
- tiiuae/Falcon-H1-0.5B-Instruct (quantized)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- falcon-llm-license
- Downloads
- 31 in the last 30 days · 253 all time · 0 likes
- Published
- 2025-06-14 · updated 2025-09-26 (1y ago)
- Tags
- falcon_h1, falcon-h1
Other MLX builds of tiiuae/Falcon-H1-0.5B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon-H1-0.5B-Instruct-4bit | 4-bit | ≈ 294 MB | 8 GB+ | 76 |
| Falcon-H1-0.5B-Instruct-5bit | 5-bit | ≈ 359 MB | 8 GB+ | 41 |
| Falcon-H1-0.5B-Instruct-6bit | 6-bit | ≈ 424 MB | 8 GB+ | 33 |
| Falcon-H1-0.5B-Instruct-8bit (this one) | 8-bit | ≈ 554 MB | 8 GB+ | 31 |
| Falcon-H1-0.5B-Instruct-bf16 | bf16 | ≈ 1.0 GB | 8 GB+ | 21 |