Get the app
← back to catalog · registered 2026-08-22 13:56

pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16

pixelkaiser Qwen 425M second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/pixelkaiser%2FHuihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16"
Response includes
  • classification m1
  • files 9
  • hub_downloads_all_time 1,438
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=pixelkaiser
All 4 models by pixelkaiser
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
1K
206 last 30d - stable
Likes
0
Model age
2mo ago
created 2026-07-17
Downloads over time
Now1.5K→from112↑1,265%
415841.1K1.7K112 on Jul 151.5K on Oct 12JulAugSepOct
Jul 15 → Oct 12 · 54 snapshots · spans 89 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated↓ 717 this lineage
pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16↓ 206

Metadata

License
apache-2.0
Tags
mlx-vlm safetensors qwen3_5_mtp mlx direct-mlx-vlm qwen3.6 mtp speculative-decoding draft-model bf16 base_model:huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated base_model:finetune:huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated

Related

Other by pixelkaiser
Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-oMLX-MTP 676 Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP 132 Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit 58
Same base model
mradermacher/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-i1-GGUF 1K mradermacher/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-GGUF 1K pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-oMLX-MTP 676 sakamakismile/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-NVFP4 353 pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP 132
Total size
810 MB
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-17 18:16
Source huggingface.co/pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16 ↗ Base model huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated →

Files by quantization

Auxiliary files 9 files 836 MB
model.safetensors 810 MB a37c3c91 download
tokenizer.json 19.1 MB 06b95093 download
vocab.json 6.41 MB 0aa0ce06 download
chat_template.jinja 7.58 KB a8755d82 download
README.md 3.15 KB 6e245d34 download
config.json 2.91 KB 4b975db9 download
MTP_DRAFTER_BUILD.json 2.64 KB e89ae643 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.14 KB 1d134cd2 download

README current version from Hugging Face

license: apache-2.0
library_name: mlx-vlm
base_model: huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated
tags:

  • mlx
  • direct-mlx-vlm
  • mlx-vlm
  • qwen3_5_mtp
  • qwen3.6
  • mtp
  • speculative-decoding
  • draft-model
  • bf16

Huihui ThinkingCap Qwen3.6 27B — direct 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+2 with MLX runtime 1.10.1 does 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:

Direct mlx-vlm

uv 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

Compatibility

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 runtime

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.

Technical details

  • MTP model type: qwen3_5_mtp
  • Block size: 3
  • MTP tensors: 15
  • MTP precision: BF16
  • Target trunk: MLX affine 4-bit, group size 64
  • Source revision: 44f63da8141407af529405c1e4b83fa39b70abe0

The drafter was extracted without changing tensor values from the MTP weights preserved in the exact upstream-derived model.

Upstream

README history 2 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-07-17Correct LM Studio compatibility boundary04d1c853.1 KB
    Loading...
  2. 2026-07-17Publish LM Studio MLX MTP drafter5ef191e2.9 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration