4-bit Open on Hugging Face
Parameters
7.6B
Weights (est.)
≈ 4.3 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-H1R-7B-4bit --prompt "Hello"
Details
- Base model
- tiiuae/Falcon-H1R-7B (quantized)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- falcon-llm-license
- Downloads
- 103 in the last 30 days · 1.7K all time · 2 likes
- Published
- 2026-01-05 · updated 2026-01-05 (10mo ago)
- Languages
- ar, cs, de, en, es, fr, hi, it, ja, ko, nl, pl, pt, ro, ru, sv, ur, zh
- Tags
- falcon_h1, falcon-h1r
Other MLX builds of tiiuae/Falcon-H1R-7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon-H1R-7B-4bit (this one) | 4-bit | ≈ 4.3 GB | 8 GB+ | 103 |
| Falcon-H1R-7B-5bit | 5-bit | ≈ 5.2 GB | 8 GB+ | 33 |
| Falcon-H1R-7B-6bit | 6-bit | ≈ 6.2 GB | 16 GB+ | 50 |
| Falcon-H1R-7B-8bit | 8-bit | ≈ 8.1 GB | 16 GB+ | 42 |
| Falcon-H1R-7B-bf16 | bf16 | ≈ 15.2 GB | 24 GB+ | 42 |