Qwen3-4B-Sky-High-Hermes-gabliterated-8bit
mlx-community/Qwen3-4B-Sky-High-Hermes-gabliterated-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
4.0B
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/Qwen3-4B-Sky-High-Hermes-gabliterated-8bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- —
- Downloads
- 54 in the last 30 days · 442 all time · 0 likes
- Published
- 2026-01-23 · updated 2026-01-23 (9mo ago)
- Tags
- qwen3, uncensored, gabliteration, model-index
Other MLX builds of Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-4B-Sky-High-Hermes-gabliterated-4bit | 4-bit | ≈ 2.3 GB | 8 GB+ | 76 |
| Qwen3-4B-Sky-High-Hermes-gabliterated-6bit | 6-bit | ≈ 3.3 GB | 8 GB+ | 33 |
| Qwen3-4B-Sky-High-Hermes-gabliterated-8bit (this one) | 8-bit | ≈ 4.3 GB | 8 GB+ | 54 |
| Qwen3-4B-Sky-High-Hermes-gabliterated-bfloat16 | — | ≈ 8.0 GB | 16 GB+ | 44 |