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

mlx-community/Huihui-GLM-4.5V-abliterated-mxfp4

mlx-community Glm 107B MoE 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/mlx-community%2FHuihui-GLM-4.5V-abliterated-mxfp4"
Response includes
  • classification m1
  • files 23
  • benchmarks 5 entries
  • hub_downloads_all_time 2,751
  • author_summary 207 models
  • readme_text full
Try next
GET/models?author=mlx-community
All 207 models by mlx-community
 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
3K
134 last 30d - cooling
Likes
3
Model age
12mo ago
created 2025-09-27
Downloads over time
Now2.8K→from23↑12,122%
01K2.1K3.1K23 on Sep 24, 20252.8K on Oct 11Sep '25Nov '25JanMarMayJulSep
Sep 24, 2025 → Oct 11 · 94 snapshots · spans 382 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Arena-Battles 1304 LM-Arena
LM Arena Elo 1328.0078804015486 LM-Arena
Arena-Elo-Lower 1311.96193218924 LM-Arena
Arena-Elo-Upper 1344.0538286138574 LM-Arena
Arena-Rank 49 LM-Arena

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-4.5V this lineage
mlx-community/Huihui-GLM-4.5V-abliterated-mxfp4↓ 134

Metadata

License
mit
Languages
zh en
Tags
mlx safetensors glm4v_moe abliterated uncensored image-text-to-text conversational zh en base_model:zai-org/GLM-4.5V base_model:quantized:zai-org/GLM-4.5V license:mit

Related

Other by mlx-community
Qwen3.8-27B-Uncensored-OptiQ-4bit 16K Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit 7K Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp 5K Josiefied-Qwen3-4B-abliterated-v1-4bit 4K Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit 4K
Same base model
mlx-community/GLM-4.5V-abliterated-4bit 68 mlx-community/GLM-4.5V-abliterated-8bit 63 mlx-community/Huihui-GLM-4.5V-abliterated-5bit 57
Total size
54.5 GB
Files
23
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-09-27 22:42
Source huggingface.co/mlx-community/Huihui-GLM-4.5V-abliterated-mxfp4 ↗ Base model zai-org/GLM-4.5V ↗

Files by quantization

Auxiliary files 23 files 54.5 GB
model-00008-of-00012.safetensors 4.98 GB 3ef555e7 download
model-00010-of-00012.safetensors 4.98 GB d9943fa8 download
model-00004-of-00012.safetensors 4.98 GB 167eb576 download
model-00006-of-00012.safetensors 4.98 GB d41074d4 download
model-00002-of-00012.safetensors 4.98 GB 17cbaa82 download
model-00001-of-00012.safetensors 4.76 GB c99dd6bb download
model-00011-of-00012.safetensors 4.72 GB ea77704b download
model-00005-of-00012.safetensors 4.72 GB 20a2ff09 download
model-00007-of-00012.safetensors 4.66 GB fdab4cf0 download
model-00009-of-00012.safetensors 4.66 GB d861afc0 download
model-00003-of-00012.safetensors 4.66 GB b45fa5bc download
model-00012-of-00012.safetensors 1.41 GB 7ec226c4 download
tokenizer.json 19.0 MB bda8e214 download
model.safetensors.index.json 143 KB 415c510d download
config.json 7.50 KB 47987a5c download
tokenizer_config.json 7.18 KB 31ceab70 download
chat_template.jinja 3.77 KB 1f6c375e download
.gitattributes 1.53 KB 52373fe2 download
video_preprocessor_config.json 890 B 5c07060b download
special_tokens_map.json 802 B 9028cf84 download
README.md 784 B d8062492 download
preprocessor_config.json 520 B 8d2b3a06 download
generation_config.json 234 B 6406f555 download

README current version from Hugging Face

language:

  • zh
  • en
    library_name: mlx
    license: mit
    pipeline_tag: image-text-to-text
    base_model:
  • zai-org/GLM-4.5V
    tags:
  • abliterated
  • uncensored
  • mlx

mlx-community/Huihui-GLM-4.5V-abliterated-mxfp4

This model was converted to MLX format from huihui-ai/Huihui-GLM-4.5V-abliterated using mlx-vlm with MXFP4 support.
Refer to the original model card for more details on the model.

Use with mlx

pip install git+https://github.com/zhutao100/mlx-vlm.git

python -m mlx_vlm.generate --model mlx-community/Huihui-GLM-4.5V-abliterated-mxfp4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

README history 2 versions

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

  1. 2025-09-27Update README.md443af22784 B
    Loading...
  2. 2025-09-27Upload folder using huggingface_hubf7bf8d3710 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