Qwen3.6-35B-A3B-MTP-bf16
This repository contains Multi-Token Prediction (MTP) drafter weights split from Qwen/Qwen3.6-35B-A3B for use with mlx-vlm speculative decoding.
This is not a standalone chat or text-generation model. Load it as the draft model alongside a compatible Qwen3.6 35B-A3B target checkpoint.
Use with mlx-vlm
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:
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.