Qwen3-4B-Instruct-2507-gabliterated-bf16
mlx-community/Qwen3-4B-Instruct-2507-gabliterated-bf16
Text generation · mlx
bf16 Open on Hugging Face
Parameters
4.0B
Weights (est.)
≈ 8.0 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/Qwen3-4B-Instruct-2507-gabliterated-bf16 --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated (finetune)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- bf16
- Licence
- —
- Downloads
- 46 in the last 30 days · 236 all time · 0 likes
- Published
- 2026-01-06 · updated 2026-01-06 (10mo ago)
- Tags
- qwen3, uncensored
Other MLX builds of Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-4B-Instruct-2507-gabliterated-4bit | 4-bit | ≈ 2.3 GB | 8 GB+ | 225 |
| Qwen3-4B-Instruct-2507-gabliterated-mxfp4 | MXFP4 | ≈ 2.3 GB | 8 GB+ | 59 |
| Qwen3-4B-Instruct-2507-gabliterated-6bit | 6-bit | ≈ 3.3 GB | 8 GB+ | 54 |
| Qwen3-4B-Instruct-2507-gabliterated-8bit | 8-bit | ≈ 4.3 GB | 8 GB+ | 57 |
| Qwen3-4B-Instruct-2507-gabliterated-bf16 (this one) | bf16 | ≈ 8.0 GB | 16 GB+ | 46 |