Downloads · 30 days
146
8% of all-time downloads
pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16
Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16 is a machine learning model from pixelkaiser. 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-vlm. The card lists the license as apache-2.0.
This is a standalone MTP draft model for direct mlx-vlm use. It is not a standalone chat model.
Downloads · 30 days
146
8% of all-time downloads
All-time downloads
1.7K
Public
Parameters
425M
869 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors849 MB · 97%
From the Hugging Face model README
mlx-vlm MTP drafter (BF16)This is a standalone MTP draft model for direct mlx-vlm use. It is not a standalone chat model.
Current LM Studio limitation: despite the historical repository name, LM Studio
0.4.19+2with MLX runtime1.10.1does not support speculative draft models for batched vision models. Do not select this as an LM Studio primary model or expect LM Studio to attach it to this Qwen3.6 VLM. For MTP, use the oMLX Native-MTP model, which is the recommended faster and more mature integrated path.
Use it with this target model:
mlx-vlmuv run mlx_vlm.generate \
--model pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit \
--draft-model pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16 \
--draft-kind mtp \
--draft-block-size 3 \
--prompt "Hello" \
--max-tokens 128
| Runtime | Use this repository as |
|---|---|
Direct mlx-vlm | MTP draft model, paired with the linked 4-bit target |
| LM Studio MLX | MTP unsupported for this batched VLM in runtime 1.10.1; use the target-only model without MTP |
| oMLX | Not this artifact; use the oMLX indexed-MTP target |
| MTPLX | Not this artifact; use the MTPLX sidecar target |
These runtimes currently use different MTP packaging contracts; the artifacts are intentionally separate.
Verified end-to-end on Apple Silicon by invoking the mlx-vlm 0.6.3 and MLX 0.31.2 packages bundled with LM Studio's MLX backend directly. A target-plus-drafter smoke generated successfully with speculative decoding active (100% of drafted tokens accepted in the bounded test; acceptance depends on the prompt). This verifies the drafter and mlx-vlm, not LM Studio's batched_vision wrapper.
qwen3_5_mtp344f63da8141407af529405c1e4b83fa39b70abe0The drafter was extracted without changing tensor values from the MTP weights preserved in the exact upstream-derived model.
mlx-vlm