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

TouchNight/gemma-2-abliterated-Ifable-9B

TouchNight Gemma 9.2B second-order
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/TouchNight%2Fgemma-2-abliterated-Ifable-9B"
Response includes
  • classification m1
  • files 18
  • benchmarks 5 entries
  • hub_downloads_all_time 159
  • author_summary 14 models
  • readme_text full
Try next
GET/models?author=TouchNight
All 14 models by TouchNight
 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
159
12 last 30d - cooling
Likes
1
Descendants
3
in 3 direct forks
Model age
23mo ago
created 2024-11-04
Downloads over time
Now166→from0↑0%
0611221830 on Oct 30, 2024166 on Oct 11Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 30, 2024 → Oct 11 · 141 snapshots · spans 711 days

Benchmarks

Benchmark Score Source
BBH average 0.5336619535607732 OpenLLM-v2
IFEval instruct 0.7865707434052758 OpenLLM-v2
IFEval-Prompt 0.7079482439926063 OpenLLM-v2
MATH lvl 5 0.0007552870090634441 OpenLLM-v2
MMLU-Pro 0.39153922872340424 OpenLLM-v2

Genealogy 3 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.

IlyaGusev/gemma-2-9b-it-abliterated↓ 442 this lineage
TouchNight/gemma-2-abliterated-Ifable-9B↓ 12 3 forks
mradermacher/gemma-2-abliterated-Ifable-9B-i1-GGUF↓ 1,081
mradermacher/gemma-2-abliterated-Ifable-9B-GGUF↓ 209
TouchNight/gemma-2-abliterated-Ifable-9B-Q4_K_M-GGUF↓ 20

Variants by this author 2 formats · 32 downloads combined

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

Metadata

Tags
safetensors gemma2 base_model:IlyaGusev/gemma-2-9b-it-abliterated base_model:finetune:IlyaGusev/gemma-2-9b-it-abliterated region:us

Related

Other by TouchNight
gemma-2-ifable-abliterated-merge-gguf 63 gemma-2-27b-it-abliterated-Q3_K_M-GGUF 50 gemma-2-27b-it-abliterated-Q3_K_S-GGUF 34 gemma-2-Ifable-abliterated-9B-untied-Q4_K_M-GGUF 31 gemma-2-27b-it-abliterated-Q2_K-GGUF 28
Same base model
bartowski/gemma-2-9b-it-abliterated-GGUF 10K BasedAGI/Gemma-2-9B-IT-Abliterated-i1-GGUF 2K tensorblock/gemma-2-9b-it-abliterated-GGUF 214 Alex01837178373/gemma-2-9b-it-abliterated-Q4_K_M-GGUF 160 KnutJaegersberg/gemma-2-9b-it-abliterated-Q8_0-GGUF 88
Total size
34.4 GB
Files
18
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-11-04 14:17
Source huggingface.co/TouchNight/gemma-2-abliterated-Ifable-9B ↗ Base model IlyaGusev/gemma-2-9b-it-abliterated →

Files by quantization

Auxiliary files 18 files 34.5 GB
model-00007-of-00008.safetensors 4.62 GB a63a1a28 download
model-00003-of-00008.safetensors 4.62 GB 6257ce1f download
model-00005-of-00008.safetensors 4.62 GB 0de4cbf1 download
model-00006-of-00008.safetensors 4.62 GB 49591231 download
model-00002-of-00008.safetensors 4.62 GB 138ebe87 download
model-00004-of-00008.safetensors 4.59 GB 0262fc10 download
model-00001-of-00008.safetensors 4.51 GB 49cf9359 download
model-00008-of-00008.safetensors 2.22 GB 8f657b48 download
tokenizer.json 32.8 MB da7c4251 download
tokenizer.model 4.04 MB 61a7b147 download
tokenizer_config.json 39.5 KB 921acf3e download
model.safetensors.index.json 38.2 KB da19758a download
.gitattributes 1.53 KB 52373fe2 download
config.json 909 B b0796047 download
special_tokens_map.json 636 B 8d6368f7 download
generation_config.json 267 B 8b4c5dba download
README.md 108 B ca40a442 download
Readme.md 54.0 B 4527f18b download

README current version from Hugging Face

base_model:

  • IlyaGusev/gemma-2-9b-it-abliterated

Merge lora extracted from Ifable with abliterated

README history 1 version

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

  1. 2024-11-04Create README.md47ab6dd108 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