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

mlx-community/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-4bit-msq

mlx-community Gemma 3.4B MoE
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-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-4bit-msq"
Response includes
  • classification m1
  • files 15
  • hub_downloads_all_time 320
  • author_summary 207 models
  • readme_text full
Try next
GET/models?author=mlx-community
All 207 models by mlx-community
 GET/models?family=gemma&method=m1
Sibling gemma 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
320
108 last 30d - stable
Likes
0
Model age
3mo ago
created 2026-06-15
Downloads over time
Now341→from52↑556%
3814825937052 on Jun 17341 on Oct 11JunJulAugSepOct
Jun 17 → Oct 11 · 56 snapshots · spans 116 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.

google/gemma-4-26B-A4B-it-qat-q4_0-unquantized this lineage
mlx-community/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-4bit-msq↓ 108

Metadata

License
apache-2.0
Tags
transformers safetensors gemma4 image-text-to-text abliterated uncensored any-to-any base_model:google/gemma-4-26B-A4B-it-qat-q4_0-unquantized base_model:quantized:google/gemma-4-26B-A4B-it-qat-q4_0-unquantized license:apache-2.0 endpoints_compatible 4-bit

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
huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-GGUF 15K sakamakismile/Huihui-gemma-4-26B-A4B-it-qat-abliterated-MTP-NVFP4 565 huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated 511 sakamakismile/Huihui-gemma-4-26B-A4B-it-qat-abliterated-pad768-NVFP4 282 llmfan46/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic 112
Total size
15.2 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-15 17:53
Source huggingface.co/mlx-community/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-4bit-msq ↗ Base model google/gemma-4-26B-A4B-it-qat-q4_0-unquantized ↗

Files by quantization

Auxiliary files 15 files 15.2 GB
model-00003-of-00004.safetensors 4.99 GB ee55ac61 download
model-00001-of-00004.safetensors 4.91 GB 9721af46 download
model-00002-of-00004.safetensors 4.90 GB 7793b3ca download
model-00004-of-00004.safetensors 362 MB 086ae5fa download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 167 KB b0f04ff1 download
config.json 44.9 KB 2e609c2e download
chat_template.jinja 16.5 KB f62ca843 download
tokenizer_config.json 2.68 KB cf6235ae download
.gitattributes 1.53 KB 52373fe2 download
README.md 924 B f48bc329 download
processor_config.json 902 B 13e92a44 download
quant_recipe.json 520 B 0e6fe0ee download
generation_config.json 203 B 5a376e9f download
.gitignore 18.0 B 62687331 download

README current version from Hugging Face

library_name: transformers
license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
pipeline_tag: any-to-any
base_model:

  • google/gemma-4-26B-A4B-it-qat-q4_0-unquantized
    tags:
  • abliterated
  • uncensored

Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated — MLX 4.3 BPW

Mixed-precision MLX quantization of huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.

Details

  • Type: Vision (VLM)
  • Average: 4.30 bits per weight
  • Method: MLX Smart Quantize (MSQ)
  • AWQ scaling: applied to 30 groups

README history 2 versions

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

  1. 2026-06-15Update README.md50365d1924 B
    Loading...
  2. 2026-06-15Add files using upload-large-folder tool4d60bde1.6 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