uv run mlx_vlm.generate \
  --model Qwen/Qwen3.6-35B-A3B \
  --draft-model mlx-community/Qwen3.6-35B-A3B-MTP-bf16 \
  --prompt "Hi, how are you?" \
  --max-tokens 256 \
  --enable-thinking

For local weights:

bash

uv run mlx_vlm.generate \
  --model /path/to/target-model \
  --draft-model /path/to/Qwen3.6-35B-A3B-mtp \
  --prompt "Hi, how are you?" \
  --max-tokens 256 \
  --enable-thinking

Model Details

Model type: qwen3_5_mtp
MTP block size: 2
Target architecture: Qwen3.6 35B-A3B
Precision: bf16
Runtime: MLX / mlx-vlm
Format: Safetensors with MLX-compatible config and tokenizer files

The stored tensors are unquantized MLX-compatible drafter weights.

Intended Use

Use this repo only as a speculative decoding drafter for compatible Qwen3.6 35B-A3B checkpoints. The target model verifies drafted tokens, while this MTP model proposes candidate tokens per decoding step.

Limitations

This checkpoint requires runtime support for Qwen/DeepSeek MTP draft models in mlx-vlm. Standard standalone generation through generic Transformers APIs is not expected to work with this repository by itself.

Please refer to the upstream Qwen/Qwen3.6-35B-A3B model card and license terms for model usage constraints.