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

mlx-community/GLM-4.5V-abliterated-8bit

mlx-community Glm 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%2FGLM-4.5V-abliterated-8bit"
Response includes
  • classification m1
  • files 35
  • benchmarks 5 entries
  • hub_downloads_all_time 1,389
  • 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
1K
63 last 30d - cooling
Likes
1
Model age
13mo ago
created 2025-08-24
Downloads over time
Now1.4K→from14↑10,014%
05191K1.6K14 on Aug 27, 20251.4K on Oct 12Aug '25Oct '25Dec '25FebAprJunAugOct
Aug 27, 2025 → Oct 12 · 99 snapshots · spans 411 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/GLM-4.5V-abliterated-8bit↓ 63

Metadata

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

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/Huihui-GLM-4.5V-abliterated-mxfp4 134 mlx-community/GLM-4.5V-abliterated-4bit 68 mlx-community/Huihui-GLM-4.5V-abliterated-5bit 57
Total size
107 GB
Files
35
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-09-05 05:27
Source huggingface.co/mlx-community/GLM-4.5V-abliterated-8bit ↗ Base model zai-org/GLM-4.5V ↗

Files by quantization

Auxiliary files 35 files 107 GB
model-00001-of-00024.safetensors 4.88 GB 08016938 download
model-00017-of-00024.safetensors 4.63 GB a020b764 download
model-00010-of-00024.safetensors 4.63 GB 7af479af download
model-00006-of-00024.safetensors 4.63 GB 3dcf78ef download
model-00019-of-00024.safetensors 4.63 GB 0ff42c10 download
model-00008-of-00024.safetensors 4.63 GB 56809b11 download
model-00011-of-00024.safetensors 4.63 GB 436127be download
model-00015-of-00024.safetensors 4.63 GB 90a0dd52 download
model-00022-of-00024.safetensors 4.63 GB b4bdbfe0 download
model-00012-of-00024.safetensors 4.63 GB 32050357 download
model-00020-of-00024.safetensors 4.63 GB 5e454eb8 download
model-00014-of-00024.safetensors 4.63 GB aba29bf9 download
model-00009-of-00024.safetensors 4.63 GB 8d6fd8ae download
model-00007-of-00024.safetensors 4.63 GB d0669015 download
model-00013-of-00024.safetensors 4.63 GB 95f58205 download
model-00021-of-00024.safetensors 4.63 GB 080dfc83 download
model-00018-of-00024.safetensors 4.63 GB 5c04552a download
model-00016-of-00024.safetensors 4.63 GB c8b73091 download
model-00005-of-00024.safetensors 4.63 GB 4c580ea9 download
model-00004-of-00024.safetensors 4.63 GB 6d0b0216 download
model-00003-of-00024.safetensors 4.63 GB 60d7742e download
model-00002-of-00024.safetensors 4.63 GB a0863a71 download
model-00023-of-00024.safetensors 4.53 GB 9b4e10da download
model-00024-of-00024.safetensors 629 MB d4c2a61d download
tokenizer.json 19.0 MB bda8e214 download
model.safetensors.index.json 1.83 MB e3b7372b download
tokenizer_config.json 7.18 KB 31ceab70 download
chat_template.jinja 3.77 KB 1f6c375e download
config.json 2.23 KB c88eb41b download
.gitattributes 1.53 KB 52373fe2 download
video_preprocessor_config.json 862 B 94dec859 download
special_tokens_map.json 802 B 9028cf84 download
README.md 676 B a0d0ea54 download
preprocessor_config.json 521 B 5837b805 download
generation_config.json 234 B 6406f555 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-4.5V
    tags:
  • abliterated
  • uncensored
  • mlx

mlx-community/GLM-4.5V-abliterated-8bit

This model was converted to MLX format from huihui-ai/Huihui-GLM-4.5V-abliterated using mlx-vlm.
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 mlx-community/GLM-4.5V-abliterated-8bit --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. 2025-09-05Update model card. (#1)189c8ca676 B
    Loading...
  2. 2025-08-24initial commit2ae41e321 B
    Loading...

Discussions 1 thread

  1. 2025-09-04PRUpdate model card.merged1 💬#1
    Loading...

Continue on Hugging Face →

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