intheblue/Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter

Qwen3.8-27B-AEON MTP Drafter (MLX)

The native multi-token-prediction head of AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 (revision 8f76e82), split into the standalone MLX drafter format that mlx-vlm expects for mtp speculative decoding. 15 tensors, BF16, 810 MB, block_size: 3.

AEON's BF16 grafts the MTP head back from stock Qwen3.8 (15 tensors, hash-matched), so this drafter is the original Qwen-trained head — not retrained.

Companion to intheblue/Qwen3.8-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-6bit; works with any MLX quantization of the same base.

How it was made

python -m mlx_vlm.speculative.drafters.qwen3_5_mtp.split \
  --model AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 \
  --output Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter

(Use the official split tool — hand-extracting mtp.* tensors produces a broken drafter with 0% acceptance: the tool applies the RMSNorm weight-convention shift and stamps format: mlx metadata.)

Usage

python -m mlx_vlm generate \
  --model intheblue/Qwen3.8-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-6bit \
  --draft-model intheblue/Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter \
  --draft-kind mtp --draft-block-size 3 \
  --prompt "..."

Speculative decoding is lossless — rejected drafts fall back to the target model's own tokens.

Measured effect

Test machine: Mac mini M4 Pro, 48 GB, with the companion 6-bit target model. Speedups carry across chips since the drafter's relative overhead is small.

Workload	Serial	With drafter
Coding (temp 0.2, block 4)	11.4 tok/s	21.5 tok/s (1.90×)
Doc QA @ 13k ctx (block 3)	~11 tok/s	16.9 tok/s
Creative prose (temp 0.7, block 3)	11.4 tok/s	15.9 tok/s (1.4×)

Block size 3 is the all-round sweet spot; block ≥5 regresses (draft accuracy decays past 2–3 tokens). Acceptance ~46% on open prose, higher on structured output.