Nanbeige4-3B-Thinking-2511-gabliterated-8bit
mlx-community/Nanbeige4-3B-Thinking-2511-gabliterated-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
3.9B
Weights (est.)
≈ 4.2 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/Nanbeige4-3B-Thinking-2511-gabliterated-8bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Nanbeige4-3B-Thinking-2511-gabliterated (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- —
- Downloads
- 18 in the last 30 days · 266 all time · 0 likes
- Published
- 2026-01-12 · updated 2026-01-13 (10mo ago)
- Tags
- llama, uncensored
Other MLX builds of Goekdeniz-Guelmez/Nanbeige4-3B-Thinking-2511-gabliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Nanbeige4-3B-Thinking-2511-gabliterated-4bit | 4-bit | ≈ 2.2 GB | 8 GB+ | 31 |
| Nanbeige4-3B-Thinking-2511-gabliterated-6bit | 6-bit | ≈ 3.2 GB | 8 GB+ | 17 |
| Nanbeige4-3B-Thinking-2511-gabliterated-8bit (this one) | 8-bit | ≈ 4.2 GB | 8 GB+ | 18 |
| Nanbeige4-3B-Thinking-2511-gabliterated-bfloat16 | — | ≈ 7.9 GB | 16 GB+ | 38 |