Falcon-H1-Tiny-90M-Instruct-4bit
mlx-community/Falcon-H1-Tiny-90M-Instruct-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
91M
Weights (est.)
≈ 51 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-Tiny-90M-Instruct-4bit --prompt "Hello"
Details
- Base model
- tiiuae/Falcon-H1-Tiny-90M-Instruct (quantized)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- falcon-llm-license
- Downloads
- 48 in the last 30 days · 302 all time · 0 likes
- Published
- 2026-01-28 · updated 2026-01-28 (9mo ago)
- Tags
- falcon_h1, falcon-h1, edge
Other MLX builds of tiiuae/Falcon-H1-Tiny-90M-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon-H1-Tiny-90M-Instruct-4bit (this one) | 4-bit | ≈ 51 MB | 8 GB+ | 48 |
| Falcon-H1-Tiny-90M-Instruct-5bit | 5-bit | ≈ 63 MB | 8 GB+ | 27 |
| Falcon-H1-Tiny-90M-Instruct-6bit | 6-bit | ≈ 74 MB | 8 GB+ | 25 |
| Falcon-H1-Tiny-90M-Instruct-8bit | 8-bit | ≈ 97 MB | 8 GB+ | 26 |
| Falcon-H1-Tiny-90M-Instruct-bf16 | bf16 | ≈ 182 MB | 8 GB+ | 24 |