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

vanch007/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-mlx-4bit

vanch007 Qwen 35B MoE multimodal 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/vanch007%2FHuihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-mlx-4bit"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 3,484
  • author_summary 27 models
  • readme_text full
Try next
GET/models?author=vanch007
All 27 models by vanch007
 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
3K
160 last 30d - cooling
Likes
2
Model age
5mo ago
created 2026-04-21
Downloads over time
Now3.5K→from1K↑247%
8941.9K2.8K3.8K1K on Apr 223.5K on Oct 11AprMayJunJulAugSepOct
Apr 22 → Oct 11 · 64 snapshots · spans 172 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-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated↓ 131 this lineage
vanch007/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-mlx-4bit↓ 160

Metadata

Tags
mlx-vlm safetensors qwen3_5_moe mlx qwen3.6 multimodal vision-language abliterated image-text-to-text conversational base_model:huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

Related

Other by vanch007
Huihui-Qwen3.5-9B-abliterated-mlx-4bit 745 Huihui-gemma-4-26B-A4B-it-abliterated-mlx-4bit 600 Huihui-Qwen3.5-9B-abliterated-mlx-8bit 370 Huihui-Qwen3.6-35B-A3B-abliterated-mlx-4bit 300 Qwen3.5-122B-A10B-abliterated-4bit-vlm-mlx-cs2764-final 241
Same base model
mradermacher/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-i1-GGUF 1K mradermacher/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-GGUF 624 batsclamp/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-FP8 142 vanch007/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-mlx-bf16 74 sakamakismile/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-NVFP4 64
Total size
19.0 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-21 17:14
Source huggingface.co/vanch007/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-mlx-4bit ↗ Base model huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated →

Files by quantization

Auxiliary files 12 files 19.0 GB
model-00002-of-00004.safetensors 5.00 GB 1af81b3d download
model-00003-of-00004.safetensors 5.00 GB 9f733bbf download
model-00001-of-00004.safetensors 4.93 GB d488d304 download
model-00004-of-00004.safetensors 4.08 GB 366282a6 download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 211 KB f714d295 download
config.json 23.1 KB 019b0587 download
chat_template.jinja 7.58 KB a8755d82 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.27 KB 7ad6acdf download
tokenizer_config.json 1.14 KB b77a523f download
README.md 776 B 1ae42bbb download

README current version from Hugging Face

library_name: mlx-vlm
pipeline_tag: image-text-to-text
base_model: huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated
base_model_relation: quantized
tags:

  • mlx
  • mlx-vlm
  • qwen3.6
  • multimodal
  • vision-language
  • abliterated

Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated-mlx-4bit

Local MLX-VLM conversion of huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated.

Overview

  • Format: MLX-VLM
  • Precision: 4bit
  • Size: 19G
  • Source model type: Qwen3_5MoeForConditionalGeneration
  • Source pipeline: image-text-to-text
  • Intended runtime: mlx-vlm, LM Studio

Validation

  • text generation smoke test: passed
  • image generation path smoke test: passed

README history 1 version

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

  1. 2026-04-21Upload MLX-VLM converted 4bit model (clean history)430f3de776 B
    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