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

nicoboss/Qwen3-30B-A3B-Thinking-2507-abliterated-CPT-SFT-sft

nicoboss Qwen 31B 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/nicoboss%2FQwen3-30B-A3B-Thinking-2507-abliterated-CPT-SFT-sft"
Response includes
  • classification m1
  • files 25
  • hub_downloads_all_time 73
  • author_summary 75 models
  • readme_text full
Try next
GET/models?author=nicoboss
All 75 models by nicoboss
 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
73
18 last 30d - stable
Likes
1
Descendants
2
in 2 direct forks
Model age
13mo ago
created 2025-09-11
Downloads over time
Now76→from4↑1,800%
02856834 on Sep 10, 202576 on Oct 1276 on Oct 11Sep '25Nov '25JanMarMayJulSep
Sep 10, 2025 → Oct 12 · 97 snapshots · spans 397 days

Genealogy 2 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.

nicoboss/Qwen3-30B-A3B-Thinking-2507-abliterated-CPT-SFT-sft↓ 18 2 forks
mradermacher/Qwen3-30B-A3B-Thinking-2507-abliterated-CPT-SFT-sft-i1-GGUF↓ 823
mradermacher/Qwen3-30B-A3B-Thinking-2507-abliterated-CPT-SFT-sft-GGUF↓ 326

Metadata

Tags
safetensors qwen3_moe region:us

Related

Other by nicoboss
Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated-llamacppfixed 81 Kimi-Dev-72B-abliterated 63 GLM-Z1-32B-0414-abliterated 59 Seed-OSS-36B-Instruct-abliterated 55 Apertus-70B-Instruct-2509-abliterated 55
Total size
56.9 GB
Files
25
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-09-11 22:51
Source huggingface.co/nicoboss/Qwen3-30B-A3B-Thinking-2507-abliterated-CPT-SFT-sft ↗

Files by quantization

Auxiliary files 25 files 56.9 GB
model-00004-of-00013.safetensors 4.65 GB 10838acb download
model-00005-of-00013.safetensors 4.65 GB afafe052 download
model-00006-of-00013.safetensors 4.65 GB 872eb2a3 download
model-00007-of-00013.safetensors 4.65 GB c6259896 download
model-00008-of-00013.safetensors 4.65 GB 59d6e2c0 download
model-00009-of-00013.safetensors 4.65 GB 6090c065 download
model-00010-of-00013.safetensors 4.65 GB 4820f879 download
model-00011-of-00013.safetensors 4.65 GB f2b65547 download
model-00012-of-00013.safetensors 4.65 GB e244e555 download
model-00003-of-00013.safetensors 4.65 GB f567df66 download
model-00002-of-00013.safetensors 4.65 GB 15dee362 download
model-00001-of-00013.safetensors 4.65 GB 5db43dd0 download
model-00013-of-00013.safetensors 1.02 GB 44c98033 download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
model.safetensors.index.json 1.62 MB ad70f197 download
merges.txt 1.59 MB 31349551 download
tokenizer_config.json 5.28 KB 1d4fba2d download
chat_template.jinja 3.95 KB 2e2f69c3 download
.gitattributes 1.53 KB 52373fe2 download
config.json 958 B a14508cf download
README.md 890 B 82838077 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 214 B f5af93d0 download

README current version from Hugging Face

Qwen3-30B-A3B-Thinking-2507-abliterated-CPT-SFT-sft

@EsotericsEnjoyer EsotericsEnjoyer/Qwen3-30B-A3B-Thinking-2507-abliterated-CPT-SFT-sft-adapters applied to
huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated as requested in https://huggingface.co/mradermacher/model_requests/discussions/1372

GGUF quants

README history 5 versions

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

  1. 2025-09-11Update README.mdb195d10890 B
    Loading...
  2. 2025-09-11Update README.mda1cc656815 B
    Loading...
  3. 2025-09-11Update README.mdbd150b0478 B
    Loading...
  4. 2025-09-11Update README.md654322c394 B
    Loading...
  5. 2025-09-11Create README.mdaa72b6c395 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