Falcon3-10B-Instruct-abliterated-4bit
mlx-community/Falcon3-10B-Instruct-abliterated-4bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
10B
Weights (est.)
≈ 5.8 GB
Mac memory (est.)
16 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/Falcon3-10B-Instruct-abliterated-4bit --prompt "Hello"
Details
- Base model
- huihui-ai/Falcon3-10B-Instruct-abliterated
- Vendor
- huihui-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- falcon-llm-license
- Downloads
- 52 in the last 30 days · 310 all time · 0 likes
- Published
- 2025-02-19 · updated 2025-02-19 (1y ago)
- Languages
- en, fr, es, pt
- Tags
- llama, falcon3, abliterated, uncensored, mlx-my-repo
Other MLX builds of huihui-ai/Falcon3-10B-Instruct-abliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Falcon3-10B-Instruct-abliterated-4bit (this one) | 4-bit | ≈ 5.8 GB | 16 GB+ | 52 |
| Falcon3-10B-Instruct-abliterated-6bit | 6-bit | ≈ 8.4 GB | 16 GB+ | 34 |
| Falcon3-10B-Instruct-abliterated-8bit | 8-bit | ≈ 10.9 GB | 16 GB+ | 31 |