Qwen/Qwen3.5-27B. In this branch, the full-precision Qwen 3.5 conversion preserves the native mtp.* tensors in a sidecar mtp.safetensors file so they can be used for native speculative decoding after MLX conversion.
- Downloads last month
- 168
Model size
27B params
Tensor type
BF16
·
F32 ·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for trevon/Qwen3.5-27B-MLX-MTP
Base model
Qwen/Qwen3.5-27B