MLX conversion of OBLITERATUS/Qwen3.6-27B-OBLITERATED for Apple Silicon.
| Base | Qwen3.6-27B-OBLITERATED |
| Architecture | qwen3_5 (mixed linear + full attention) |
| Parameters | 26.9B |
| Quantization | 4-bit affine, group_size 64 |
| Format | MLX safetensors (3 shards, ~14 GB) |
| Context window | 262,144 tokens |
| Tokenizer | Qwen2Tokenizer with tool-call support |
The model uses an alternating linear/full attention pattern across 64 layers (mamba-style linear attention interleaved with standard multi-head attention), giving it efficient long-context performance on Apple Silicon.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("edward-lcl/Qwen3.6-27B-OBLITERATED-MLX-4bit")
response = generate(model, tokenizer, prompt="Your prompt here", max_tokens=512)
print(response)
mlx_lm.generate \
--model edward-lcl/Qwen3.6-27B-OBLITERATED-MLX-4bit \
--prompt "Your prompt here" \
--max-tokens 512
| Temperature | 0.35 |
| Repetition penalty | 1.05 |
| top_p | 1.0 |
chat_template.jinja with full tool-call formattingOriginal model: OBLITERATUS/Qwen3.6-27B-OBLITERATED
model-00002-of-00003.safetensors 5.4 GBmodel-00001-of-00003.safetensors 5.3 GBmodel-00003-of-00003.safetensors 4.5 GBOBLITERATUS/Qwen3.6-27B-OBLITERATED