Downloads · 30 days
8
22% of all-time downloads
Qwen3.6-27B-MTP-bf16
ToPo-ToPo/Qwen3.6-27B-MTP-bf16
Qwen3.6-27B-MTP-bf16 is a machine learning model from ToPo-ToPo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
MTP (multi-token prediction) drafter for speculative decoding with Qwen/Qwen3.6-27B on Apple Silicon (mlx-vlm).
All-time downloads
37
Public
Parameters
425M
862 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors849 MB · 98%
At a glance
- Library
- mlx
- License
- apache-2.0
- Model type
- qwen3_5_mtp
- Access
- Public
- Created
- Aug 27, 2026
- Updated
- Aug 27, 2026
- SHA
- 7245f6f1
Base models
Model card
From the Hugging Face model README
ToPo-ToPo/Qwen3.6-27B-MTP-bf16
MTP (multi-token prediction) drafter for speculative decoding with
Qwen/Qwen3.6-27B on Apple Silicon (mlx-vlm).
This is not a standalone chat model — it only works bound to a Qwen3.6-27B target model.
Provenance
- Split from the official checkpoint's built-in
mtp.*weights (15 tensors) with mlx-vlm 0.6.13:python -m mlx_vlm.speculative.drafters.qwen3_5_mtp.split --model Qwen/Qwen3.6-27B --output . - Precision: bf16 (unquantized, split as-is)
- Size: 829 MB,
block_size: 3,model_type: qwen3_5_mtp
Usage
mlx_vlm.generate --model ToPo-ToPo/Qwen3.6-27B-mlx-4bit \
--draft-model ToPo-ToPo/Qwen3.6-27B-MTP-bf16 --draft-kind mtp \
--prompt "..." --max-tokens 400
Quantized targets share this drafter (under greedy decoding the drafter's argmax rarely changes with target quantization). Speedup depends on hardware, target quantization, workload and the mlx-vlm version — measure it yourself.
- Library
- mlx
- Type
- qwen3_5_mtp
- License
- apache-2.0
- Created
- Aug 27, 2026
- Updated
- Aug 27, 2026