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

matatonic/Qwen2.5-72B-Instruct-abliterated-v2-6.5bpw-h8-exl2

matatonic Qwen 72B
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/matatonic%2FQwen2.5-72B-Instruct-abliterated-v2-6.5bpw-h8-exl2"
Response includes
  • classification m1
  • files 18
  • benchmarks 5 entries
  • hub_downloads_all_time 199
  • author_summary 16 models
  • readme_text full
Try next
GET/models?author=matatonic
All 16 models by matatonic
 GET/models?family=qwen&method=m1
Sibling qwen 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
199
26 last 30d - stable
Likes
2
Model age
20mo ago
created 2025-01-19
Downloads over time
Now209→from2↑10,350%
0771532302 on Jan 15, 2025209 on Oct 11209 on Oct 10Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 15, 2025 → Oct 11 · 130 snapshots · spans 634 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
BBH average 0.6161629264496044 OpenLLM-v2
IFEval instruct 0.46882494004796166 OpenLLM-v2
IFEval-Prompt 0.3585951940850277 OpenLLM-v2
MATH lvl 5 0.3610271903323263 OpenLLM-v2
MMLU-Pro 0.5968251329787234 OpenLLM-v2

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.

Qwen/Qwen2.5-72B this lineage
matatonic/Qwen2.5-72B-Instruct-abliterated-v2-6.5bpw-h8-exl2↓ 26

Metadata

License
other
Languages
zho eng fra spa por deu ita rus jpn kor vie tha ara
Tags
transformers safetensors qwen2 text-generation chat conversational zho eng fra spa por deu

Related

Other by matatonic
GLM-4-32B-0414-abliterated-Q6_K-GGUF 69 GLM-4-32B-0414-abliterated-Q5_K_S-GGUF 46 GLM-4-32B-0414-abliterated-Q8_0-GGUF 44 DeepSeek-R1-Distill-Llama-70B-abliterated-6.5bpw-h8-exl2 33 Llama-3.2-3B-Instruct-abliterated-6.5bpw-h8-exl2 23
Same base model
zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-GGUF 992 zetasepic/Qwen2.5-72B-Instruct-abliterated-v2 34 zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-5.0bpw-exl2 21 matatonic/Qwen2.5-72B-Instruct-abliterated-v2-4.5bpw-exl2 18
Total size
56.5 GB
Files
18
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-28 19:57
Source huggingface.co/matatonic/Qwen2.5-72B-Instruct-abliterated-v2-6.5bpw-h8-exl2 ↗ Base model Qwen/Qwen2.5-72B ↗

Files by quantization

Auxiliary files 18 files 56.5 GB
output-00004-of-00006.safetensors 9.89 GB 2be80f73 download
output-00002-of-00006.safetensors 9.84 GB 5d4370cb download
output-00001-of-00006.safetensors 9.82 GB f3dac952 download
output-00005-of-00006.safetensors 9.81 GB da723814 download
output-00003-of-00006.safetensors 9.80 GB 03296e37 download
output-00006-of-00006.safetensors 7.34 GB 853853ed download
tokenizer.json 6.71 MB d24314ef download
measurement.json 4.26 MB 0f5c8e55 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 77.2 KB ac262537 download
tokenizer_config.json 7.13 KB 8adf747c download
.gitattributes 1.48 KB a6344aac download
config.json 1.02 KB 0956ec43 download
README.md 966 B b8aef572 download
special_tokens_map.json 613 B ac23c0aa download
added_tokens.json 605 B 482ced46 download
generation_config.json 243 B 64d27602 download

README current version from Hugging Face

license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
language:

  • zho
  • eng
  • fra
  • spa
  • por
  • deu
  • ita
  • rus
  • jpn
  • kor
  • vie
  • tha
  • ara
    pipeline_tag: text-generation
    base_model: Qwen/Qwen2.5-72B
    tags:
  • chat
    library_name: transformers

Abliterated version of Qwen/Qwen2.5-72B-Instruct, utilizing code from refusal_direction.

For more information about the Abliterated technique, refer to this article and check out @FailSpy.

GGUF

Try harder to remove admonition and moral appeal

This model is licensed under the Qwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.

README history 2 versions

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

  1. 2025-04-28Improve language tag (#2)bb50055932 B
    Loading...
  2. 2025-01-19initiale812aa2860 B
    Loading...

Discussions 2 threads

  1. 2025-04-27PRImprove language tagmerged1 💬#2
    Loading...
  2. 2025-02-28Can you produce a 4.5bpw quantized model of this model?closed3 💬#1
    Loading...

Continue on Hugging Face →

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