Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-8Bit
mlx-community/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-8Bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 28.6 GB
Mac memory (est.)
48 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/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-8Bit --prompt "Hello"
Details
- Base model
- AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 (quantized)
- Vendor
- AEON-7
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 1.2K in the last 30 days · 27K all time · 25 likes
- Published
- 2026-04-30 · updated 2026-05-13 (6mo ago)
- Languages
- en, zh, multilingual
- Tags
- qwen3_5, image-text-to-text, abliterated, uncensored, qwen3, qwen3.6, bf16, bfloat16, hybrid-attention, mamba, gated-deltanet, abliterix
Other MLX builds of AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-2Bit | 2-bit | ≈ 8.4 GB | 16 GB+ | 807 |
| Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-3Bit | 3-bit | ≈ 11.8 GB | 16 GB+ | 14 |
| Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-4Bit | 4-bit | ≈ 15.1 GB | 24 GB+ | 41 |
| Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-5Bit | 5-bit | ≈ 18.5 GB | 24 GB+ | 24 |
| Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-6Bit | 6-bit | ≈ 21.9 GB | 32 GB+ | 26 |
| Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-8Bit (this one) | 8-bit | ≈ 28.6 GB | 48 GB+ | 1.2K |
| Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-fp16 | bf16 | ≈ 53.8 GB | 64 GB+ | 169 |