6-bit Open on Hugging Face
Parameters
759M
Weights (est.)
≈ 622 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-E-3B-Instruct-6bit --prompt "Hello"
Details
- Base model
- tiiuae/Falcon-E-3B-Instruct (quantized)
- Vendor
- TII · Falcon
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- falcon-llm-license
- Downloads
- 23 in the last 30 days · 159 all time · 0 likes
- Published
- 2025-06-10 · updated 2025-06-10 (1y ago)
- Tags
- llama, bitnet, falcon-e
Other MLX builds of tiiuae/Falcon-E-3B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon-E-3B-Instruct-6bit (this one) | 6-bit | ≈ 622 MB | 8 GB+ | 23 |
| Falcon-E-3B-Instruct-8bit | 8-bit | ≈ 820 MB | 8 GB+ | 24 |
| Falcon-E-3B-Instruct-4bit | 4-bit | ≈ 839 MB | 8 GB+ | 36 |
| Falcon-E-3B-Instruct-1.58bit | 58-bit | ≈ 999 MB | 8 GB+ | 49 |