bf16 Open on Hugging Face
Parameters
1.6B
Weights (est.)
≈ 3.1 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/Falcon-H1-1.5B-Instruct-bf16 --prompt "Hello"
Details
- Base model
- tiiuae/Falcon-H1-1.5B-Instruct (finetune)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- bf16
- Licence
- falcon-llm-license
- Downloads
- 32 in the last 30 days · 286 all time · 0 likes
- Published
- 2025-06-14 · updated 2025-06-16 (1y ago)
- Tags
- falcon_h1, falcon-h1
Other MLX builds of tiiuae/Falcon-H1-1.5B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon-H1-1.5B-Instruct-4bit | 4-bit | ≈ 875 MB | 8 GB+ | 79 |
| Falcon-H1-1.5B-Instruct-5bit | 5-bit | ≈ 1.1 GB | 8 GB+ | 30 |
| Falcon-H1-1.5B-Instruct-6bit | 6-bit | ≈ 1.3 GB | 8 GB+ | 29 |
| Falcon-H1-1.5B-Instruct-8bit | 8-bit | ≈ 1.7 GB | 8 GB+ | 32 |
| Falcon-H1-1.5B-Instruct-bf16 (this one) | bf16 | ≈ 3.1 GB | 8 GB+ | 32 |