Granite-4.0-350m-gabliterated-6bit
mlx-community/Granite-4.0-350m-gabliterated-6bit
Text generation · mlx
6-bit Open on Hugging Face
Parameters
352M
Weights (est.)
≈ 286 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/Granite-4.0-350m-gabliterated-6bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Granite-4.0-350m-gabliterated (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- —
- Downloads
- 24 in the last 30 days · 126 all time · 0 likes
- Published
- 2026-01-23 · updated 2026-01-23 (9mo ago)
- Tags
- granitemoehybrid, uncensored, gabliteration, model-index
Other MLX builds of Goekdeniz-Guelmez/Granite-4.0-350m-gabliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Granite-4.0-350m-gabliterated-4bit | 4-bit | ≈ 198 MB | 8 GB+ | 22 |
| Granite-4.0-350m-gabliterated-6bit (this one) | 6-bit | ≈ 286 MB | 8 GB+ | 24 |
| Granite-4.0-350m-gabliterated-8bit | 8-bit | ≈ 374 MB | 8 GB+ | 20 |
| Granite-4.0-350m-gabliterated-bfloat16 | — | ≈ 705 MB | 8 GB+ | 22 |