Josiefied-Qwen3-0.6B-abliterated-v1-float32
mlx-community/Josiefied-Qwen3-0.6B-abliterated-v1-float32
Text generation · mlx
Parameters
596M
Weights (est.)
≈ 2.4 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/Josiefied-Qwen3-0.6B-abliterated-v1-float32 --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v1 (finetune)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- Not stated
- Licence
- —
- Downloads
- 31 in the last 30 days · 375 all time · 0 likes
- Published
- 2025-05-05 · updated 2025-05-05 (1y ago)
- Tags
- qwen3, chat
Other MLX builds of Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josiefied-Qwen3-0.6B-abliterated-v1-4bit | 4-bit | ≈ 335 MB | 8 GB+ | 69 |
| Josiefied-Qwen3-0.6B-abliterated-v1-6bit | 6-bit | ≈ 484 MB | 8 GB+ | 47 |
| Josiefied-Qwen3-0.6B-abliterated-v1-8bit | 8-bit | ≈ 633 MB | 8 GB+ | 37 |
| Josiefied-Qwen3-0.6B-abliterated-v1-bf16 | bf16 | ≈ 1.2 GB | 8 GB+ | 34 |
| Josiefied-Qwen3-0.6B-abliterated-v1-float32 (this one) | — | ≈ 2.4 GB | 8 GB+ | 31 |