← back to catalog · registered 2026-11-21 23:04

FarhadSu/Gemma-4-26B-A4B-Uncensored-GGUF

FarhadSu Gemma 26B GGUF 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/FarhadSu%2FGemma-4-26B-A4B-Uncensored-GGUF"
Response includes
  • classification m8
  • files 3
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
1
Model age
today
created 2026-11-21
Downloads over time
Now 0 → from 0 ↑ 0%
0011 0 on Nov 21 0 on Nov 22 Nov
Nov 21 → Nov 22 · 2 snapshots · spans 1 day

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.

Metadata

License
other
Tags
gguf llama.cpp gemma4 moe uncensored abliterated imatrix iq3_xxs text-generation license:other endpoints_compatible region:us

Related

Control vectors

Total size
10.5 GB
Files
3
Quantizations
1
Registered
2026-11-21 23:04
Last updated on HF
2026-11-21 23:17

Files by quantization

Auxiliary files 3 files 10.5 GB
Gemma-4-26B-A4B-Uncensored-IQ3_XXS-imx.gguf 10.5 GB 73440c05 download
README.md 1.85 KB 99de16a1 download
.gitattributes 1.56 KB 71e217e6 download

README current version from Hugging Face


base_model: google/gemma-4-26b-a4b-it
tags: [gguf, llama.cpp, gemma4, moe, uncensored, abliterated, imatrix, iq3_xxs]
pipeline_tag: text-generation
license: other
license_link: https://huggingface.co/google/gemma-4-26b-a4b-it

Gemma-4-26B-A4B-Uncensored — IQ3_XXS (imatrix) GGUF

Single-file IQ3_XXS GGUF (11.2 GB) of an uncensored (abliterated) Gemma 4 26B-A4B MoE instruct model, made to fit a 16 GB VRAM box with long context.

How it was made

  • Source: FarhadSu uncensored FP8 checkpoint of google/gemma-4-26b-a4b-it.
  • HF → GGUF Q8_0 with llama.cpp convert_hf_to_gguf.py (patched so fused expert tensors ffn_gate_up_exps.weight are written and quantized correctly).
  • Importance matrix: 66 × 512-token chunks of an English coding/agent calibration corpus.
  • llama-quantize IQ3_XXS --imatrix, output tensor IQ4_NL.

Tested (llama.cpp Vulkan, 2× RX 580 8 GB, KV q8_0, flash-attn on)

Test Result
Code (n-th prime) ✅ correct
Reasoning (bat & ball, widgets) ✅ correct
Uncensored (lock picking explanation) ✅ answers, no refusal
Needle-in-haystack 4K / 16K / 30K ✅ / ✅ / ✅
Context 256K loads, 14.8 GB VRAM; 117K prompt peaked at 15.6 GB

Speed: generation 27–34 t/s; prompt processing 292 t/s @4K, 192 @16K, 128 @30K, ~55 @117K (ubatch-size 256 was fastest).

Known limitations

  • Retrieval verified only up to 30K tokens; beyond that untested (and slow on this hardware).
  • Low-resource languages (e.g. Azerbaijani) can fall into repetition loops, likely due to English-only imatrix + 3-bit quant.
  • Uncensored: the model will not refuse harmful requests. You are responsible for how you use it.

Usage

llama-server -m Gemma-4-26B-A4B-Uncensored-IQ3_XXS-imx.gguf -ngl 99 -c 32768 -fa on \
  --cache-type-k q8_0 --cache-type-v q8_0 -ub 256 --jinja --temp 1.0 --top-p 0.95 --top-k 64

README history 3 versions

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

  1. 2026-11-21 Upload README.md with huggingface_hub 2058dac 2.2 KB
    Loading...
  2. 2026-11-21 Upload README.md with huggingface_hub e25b120 2 KB
    Loading...
  3. 2026-11-21 Upload README.md with huggingface_hub 15cae21 1.9 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.

Open in Abliteration