Josiefied-Qwen3-30B-A3B-abliterated-v2-bf16
mlx-community/Josiefied-Qwen3-30B-A3B-abliterated-v2-bf16
Text generation · mlx
bf16 Open on Hugging Face
Parameters
31B
Weights (est.)
≈ 61.1 GB
Mac memory (est.)
96 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-Qwen3-30B-A3B-abliterated-v2-bf16 --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2 (finetune)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- bf16
- Licence
- —
- Downloads
- 42 in the last 30 days · 824 all time · 0 likes
- Published
- 2025-06-19 · updated 2025-06-19 (1y ago)
- Tags
- qwen3_moe, chat
Other MLX builds of Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josiefied-Qwen3-30B-A3B-abliterated-v2-4bit | 4-bit | ≈ 17.2 GB | 24 GB+ | 738 |
| Josiefied-Qwen3-30B-A3B-abliterated-v2-6bit | 6-bit | ≈ 24.8 GB | 32 GB+ | 42 |
| Josiefied-Qwen3-30B-A3B-abliterated-v2-8bit | 8-bit | ≈ 32.4 GB | 48 GB+ | 74 |
| Josiefied-Qwen3-30B-A3B-abliterated-v2-bf16 (this one) | bf16 | ≈ 61.1 GB | 96 GB+ | 42 |