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

mergekit-community/Tigers-Abliterated-Upscaled

mergekit-community Gemma 16B 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/mergekit-community%2FTigers-Abliterated-Upscaled"
Response includes
  • classification m5
  • files 16
  • benchmarks 11 entries
  • hub_downloads_all_time 33
  • author_summary 6 models
  • readme_text full
Try next
GET/models?author=mergekit-community
All 6 models by mergekit-community
 GET/models?family=gemma&method=m5
Sibling gemma models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
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 · lifetime
33
13 last 30d - stable
Likes
0
Descendants
1
in 1 direct fork
Model age
20mo ago
created 2025-02-17
Downloads over time
Now43→from0↑0%
01734520 on Feb 12, 202543 on Oct 1147 on Sep 10, 2025Feb '25May '25Aug '25Nov '25FebMayAug
Feb 12, 2025 → Oct 11 · 126 snapshots · spans 606 days

Benchmarks

Benchmark Score Source
Entertainment 0.6 UGI
Hazardous 3.5 UGI
Natural Intelligence 15.71 UGI
Political lean -20.9% UGI
Sensitive-Info 16.09 UGI
SocPol 1.3 UGI
UGI 28.23 UGI
Willingness (10) 5.2 UGI
W10-Adherence 4.5 UGI
W10-Direct 6 UGI
Writing 29.22 UGI

Genealogy 1 direct fork

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

mergekit-community/Tigers-Abliterated-9B↓ 20 this lineage
mergekit-community/Tigers-Abliterated-Upscaled↓ 13 1 fork
mradermacher/Tigers-Abliterated-Upscaled-GGUF↓ 205

Metadata

Tags
transformers safetensors gemma2 text-generation mergekit merge conversational base_model:mergekit-community/Tigers-Abliterated-9B base_model:finetune:mergekit-community/Tigers-Abliterated-9B text-generation-inference endpoints_compatible region:us

Related

Other by mergekit-community
Llama-3-DeepSeek-R1-Distill-8B-LewdPlay-Uncensored 239 Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated 29 Llama-3-LewdPlay-DeepSeek-R1-Distill-8B-abliterated 24 Tigers-Abliterated-9B 20 uncensored-mix 18
Same base model
mradermacher/Tigers-Abliterated-9B-i1-GGUF 623 mradermacher/Tigers-Abliterated-9B-GGUF 204
Total size
29.0 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-17 06:53
Source huggingface.co/mergekit-community/Tigers-Abliterated-Upscaled ↗ Base model mergekit-community/Tigers-Abliterated-9B →

Files by quantization

Auxiliary files 16 files 29.1 GB
model-00004-of-00007.safetensors 4.65 GB 3a1d476b download
model-00001-of-00007.safetensors 4.65 GB 66bbad48 download
model-00002-of-00007.safetensors 4.64 GB ed1758f0 download
model-00003-of-00007.safetensors 4.62 GB 8ea4e604 download
model-00006-of-00007.safetensors 4.62 GB 800edb44 download
model-00005-of-00007.safetensors 4.57 GB 84513c68 download
model-00007-of-00007.safetensors 1.29 GB 2cb4e43f download
tokenizer.json 32.8 MB da7c4251 download
tokenizer.model 4.04 MB 61a7b147 download
model.safetensors.index.json 64.0 KB 7b6e3691 download
tokenizer_config.json 39.5 KB a4beb468 download
.gitattributes 1.53 KB 52373fe2 download
README.md 934 B 92f96a3d download
config.json 915 B a1c296c7 download
special_tokens_map.json 636 B 8d6368f7 download
mergekit_config.yml 329 B 8e403ce9 download

README current version from Hugging Face

base_model:

  • mergekit-community/Tigers-Abliterated-9B
    library_name: transformers
    tags:
  • mergekit
  • merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: passthrough
dtype: bfloat16
slices:
  - sources:
    - model: mergekit-community/Tigers-Abliterated-9B
      layer_range: [0,42]
  - sources:
    - model: mergekit-community/Tigers-Abliterated-9B
      layer_range: [0,16]
  - sources:
    - model: mergekit-community/Tigers-Abliterated-9B
      layer_range: [26,42]

README history 1 version

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

  1. 2025-02-17Upload folder using huggingface_hub7caf489934 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