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

SzilviaB/Gemma2_Magnum_abliterated_27b

SzilviaB Gemma 27B 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/SzilviaB%2FGemma2_Magnum_abliterated_27b"
Response includes
  • classification m5
  • files 21
  • hub_downloads_all_time 59
  • author_summary 22 models
  • readme_text full
Try next
GET/models?author=SzilviaB
All 22 models by SzilviaB
 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
59
23 last 30d - stable
Likes
1
Descendants
5
in 5 direct forks
Model age
23mo ago
created 2024-10-26
Downloads over time
Now66→from16↑313%
0377511216 on Oct 23, 202466 on Oct 11102 on Sep 10, 2025Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 23, 2024 → Oct 11 · 142 snapshots · spans 718 days

Genealogy 5 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.

byroneverson/gemma-2-27b-it-abliterated↓ 71 this lineage
SzilviaB/Gemma2_Magnum_abliterated_27b↓ 23 5 forks
mradermacher/Gemma2_Magnum_abliterated_27b-i1-GGUF↓ 715
mradermacher/Gemma2_Magnum_abliterated_27b-GGUF↓ 460
SzilviaB/Gemma2_Magnum_abliterated_27b-Q4_K_M-GGUF↓ 81
SzilviaB/Gemma2_Magnum_abliterated_27b-Q5_K_M-GGUF↓ 17
SzilviaB/Gemma2_Magnum_abliterated_27b-Q8_0-GGUF↓ 14

Variants by this author 3 formats · 121 downloads combined

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

Metadata

Tags
transformers safetensors gemma2 text-generation mergekit merge conversational base_model:anthracite-org/magnum-v4-27b base_model:merge:anthracite-org/magnum-v4-27b base_model:byroneverson/gemma-2-27b-it-abliterated base_model:merge:byroneverson/gemma-2-27b-it-abliterated text-generation-inference

Related

Other by SzilviaB
SzilviaB-Daredevil-LongWriter-8B_abliterated 89 Gemma2_Magnum_abliterated_27b-Q4_K_M-GGUF 81 Daredevil-Aura-8B_uncensored_OAS_abliterated-Q8_0-GGUF 41 SzilviaB_Astral-Cydonia-22B_abliterated_broken_but_in_a_nice_way-Q8_0-GGUF 30 Daredevil-Aura-8B_uncensored_OAS_abliterated 23
Same base model
QuantFactory/gemma-2-27b-it-abliterated-GGUF 1K mradermacher/gemma-2-27b-it-abliterated-i1-GGUF 1K mradermacher/gemma-2-27b-it-abliterated-GGUF 600 tensorblock/gemma-2-27b-it-abliterated-GGUF 203 byroneverson/gemma-2-27b-it-abliterated-gguf 136
Total size
50.7 GB
Files
21
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-10-26 19:07
Source huggingface.co/SzilviaB/Gemma2_Magnum_abliterated_27b ↗ Base model byroneverson/gemma-2-27b-it-abliterated →

Files by quantization

Auxiliary files 21 files 50.8 GB
model-00003-of-00012.safetensors 4.64 GB 645177b5 download
model-00006-of-00012.safetensors 4.64 GB 959dd605 download
model-00009-of-00012.safetensors 4.64 GB a311f6ba download
model-00001-of-00012.safetensors 4.62 GB 9d40c73a download
model-00007-of-00012.safetensors 4.54 GB 6d91f7fe download
model-00010-of-00012.safetensors 4.54 GB 14631c6b download
model-00004-of-00012.safetensors 4.54 GB 938af6d0 download
model-00002-of-00012.safetensors 4.54 GB f698eed5 download
model-00005-of-00012.safetensors 4.54 GB d32efe32 download
model-00008-of-00012.safetensors 4.54 GB d085b06f download
model-00011-of-00012.safetensors 4.54 GB a2fe4c88 download
model-00012-of-00012.safetensors 432 MB 0a925b8c download
tokenizer.json 32.8 MB 5f7eee61 download
tokenizer.model 4.04 MB 61a7b147 download
tokenizer_config.json 45.9 KB 36ba1287 download
model.safetensors.index.json 39.8 KB 47d051d9 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1014 B dc6d35bb download
config.json 915 B 03db8f33 download
special_tokens_map.json 636 B 8d6368f7 download
mergekit_config.yml 301 B 45c1bae5 download

README current version from Hugging Face

base_model:

  • byroneverson/gemma-2-27b-it-abliterated
  • anthracite-org/magnum-v4-27b
    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 SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: byroneverson/gemma-2-27b-it-abliterated
  - model: anthracite-org/magnum-v4-27b
merge_method: slerp
base_model: byroneverson/gemma-2-27b-it-abliterated
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers

README history 1 version

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

  1. 2024-10-26Upload folder using huggingface_hub72cf0d21014 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