Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-bf16
mlx-community/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-bf16
Text generation · mlx
bf16 Open on Hugging Face
Parameters
8.2B
Weights (est.)
≈ 16.4 GB
Mac memory (est.)
24 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-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-bf16 --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1 (finetune)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- bf16
- Licence
- —
- Downloads
- 86 in the last 30 days · 7.3K all time · 1 likes
- Published
- 2025-05-29 · updated 2025-05-29 (1y ago)
- Tags
- qwen3, chat
Other MLX builds of Goekdeniz-Guelmez/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-4bit | 4-bit | ≈ 4.6 GB | 8 GB+ | 274 |
| Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-8bit | 8-bit | ≈ 8.7 GB | 16 GB+ | 131 |
| Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-bf16 (this one) | bf16 | ≈ 16.4 GB | 24 GB+ | 86 |