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

alexgusevski/Huihui-GLM-4.6V-Flash-abliterated-q2-mlx

alexgusevski Glm 9.4B multimodal
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/alexgusevski%2FHuihui-GLM-4.6V-Flash-abliterated-q2-mlx"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 568
  • author_summary 64 models
  • readme_text full
Try next
GET/models?author=alexgusevski
All 64 models by alexgusevski
 GET/models?family=glm&method=m1
Sibling glm 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
568
76 last 30d - stable
Likes
0
Model age
9mo ago
created 2026-01-11
Downloads over time
Now589→from26↑2,165%
021543064526 on Jan 14589 on Oct 11JanMarMayJulSep
Jan 14 → Oct 11 · 78 snapshots · spans 270 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.

zai-org/GLM-4.6V-Flash this lineage
alexgusevski/Huihui-GLM-4.6V-Flash-abliterated-q2-mlx↓ 76

Variants by this author 5 formats · 320 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
mit
Languages
zh en
Tags
transformers safetensors glm4v image-text-to-text abliterated uncensored mlx conversational zh en base_model:zai-org/GLM-4.6V-Flash base_model:quantized:zai-org/GLM-4.6V-Flash

Related

Other by alexgusevski
Huihui-Qwen3-VL-8B-Instruct-abliterated-q8-mlx 437 Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-mlx-8Bit 347 Huihui-Qwen3-VL-8B-Instruct-abliterated-q4-mlx 278 Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-fp16 263 Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-2Bit 205
Same base model
AliBilge/Huihui-GLM-4.6V-Flash-abliterated 1K huihui-ai/Huihui-GLM-4.6V-Flash-abliterated 156 alexgusevski/Huihui-GLM-4.6V-Flash-abliterated-q4-mlx 84 alexgusevski/Huihui-GLM-4.6V-Flash-abliterated-q3-mlx 55 alexgusevski/Huihui-GLM-4.6V-Flash-abliterated-q8-mlx 55
Total size
4.40 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-01-11 15:08
Source huggingface.co/alexgusevski/Huihui-GLM-4.6V-Flash-abliterated-q2-mlx ↗ Base model zai-org/GLM-4.6V-Flash ↗

Files by quantization

Auxiliary files 12 files 4.42 GB
model.safetensors 4.40 GB 251136ee download
tokenizer.json 19.0 MB f0ccf225 download
model.safetensors.index.json 98.0 KB 15fee224 download
chat_template.jinja 4.50 KB efe6364a download
config.json 2.13 KB fae51dc7 download
processor_config.json 1.92 KB d3409e73 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.43 KB a60cd3e0 download
README.md 741 B f97d950b download
video_preprocessor_config.json 369 B cc98c707 download
preprocessor_config.json 367 B 30855369 download
generation_config.json 257 B 82aa66fe download

README current version from Hugging Face

language:

  • zh
  • en
    library_name: transformers
    license: mit
    pipeline_tag: image-text-to-text
    base_model:
  • zai-org/GLM-4.6V-Flash
    tags:
  • abliterated
  • uncensored
  • mlx

alexgusevski/Huihui-GLM-4.6V-Flash-abliterated-q2-mlx

This model was converted to MLX format from huihui-ai/Huihui-GLM-4.6V-Flash-abliterated using mlx-vlm version 0.3.10.
Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model alexgusevski/Huihui-GLM-4.6V-Flash-abliterated-q2-mlx --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

README history 1 version

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

  1. 2026-01-11Upload folder using huggingface_hubf982cb2741 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