Get the app
← back to catalog · registered 2026-10-11 20:59

AI-conn/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF

AI-conn 30B GGUF MoE 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/AI-conn%2FHuihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF"
Response includes
  • classification m-uncensored
  • files 26
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=AI-conn
All 3 models by AI-conn
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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 · 30-day
0
Likes
0
Model age
today
created 2026-10-11

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.

huihui-ai/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated↓ 11,981 this lineage
AI-conn/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF

Metadata

License
apache-2.0
Quantizations
IQ1 IQ2 IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5_K Q6_K
Tags
gguf uncensored abliterated code moe ollama base_model:huihui-ai/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated license:apache-2.0 endpoints_compatible region:us imatrix

Related

Other by AI-conn
Huihui-Qwen3.8-27B-abliterated-GGUF 0 GLM-4.7-Flash-Uncensored-HauhauCS-Balanced 0
Same base model
mradermacher/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF 45K mradermacher/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-GGUF 16K SAPSAN-SKLEP/HIDra-30B-A3B-GGUF-uncensored-cybersec 4K Thaurock/Qwen3-Coder-30B-A3B-Instruct-abliterated-GGUF 3K marafx2007/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF 1K
Total size
302 GB
Files
26
Quantizations
11
Registered
2026-10-11 20:59
Last updated on HF
2026-10-11 20:21
Source huggingface.co/AI-conn/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF ↗ Base model huihui-ai/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated →

Files by quantization

Q6_K 1 file 23.4 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q6_K.gguf 23.4 GB 72aafefc download
Q5_K 2 files 39.9 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q5_K_M.gguf 20.2 GB 1ebc1d74 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q5_K_S.gguf 19.6 GB db6a9427 download
Q4 2 files 34.1 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q4_1.gguf 17.9 GB 2e809e7e download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q4_0.gguf 16.2 GB aaa43d96 download
Q4_K 2 files 33.5 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q4_K_M.gguf 17.3 GB bf6c1462 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q4_K_S.gguf 16.3 GB 3602ace5 download
IQ4 1 file 15.2 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ4_XS.gguf 15.2 GB dfa0d825 download
Q3_K 3 files 40.9 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q3_K_L.gguf 14.8 GB 8ecce725 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q3_K_M.gguf 13.7 GB 00e4bd52 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q3_K_S.gguf 12.4 GB 2b0e685b download
IQ3 4 files 47.7 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ3_M.gguf 12.6 GB e8b5f2ad download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ3_S.gguf 12.4 GB d08b31d5 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ3_XS.gguf 11.7 GB 23ae77b3 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ3_XXS.gguf 11.0 GB 4613c7c7 download
Q2_K 2 files 20.3 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q2_K.gguf 10.5 GB 030560ef download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q2_K_S.gguf 9.80 GB 5d108ced download
IQ2 4 files 34.2 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ2_M.gguf 9.47 GB bb4dba66 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ2_S.gguf 8.65 GB a12b80b5 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ2_XS.gguf 8.45 GB 29560e40 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ2_XXS.gguf 7.62 GB 918625c7 download
IQ1 2 files 12.6 GB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ1_M.gguf 6.59 GB 6687c9b3 download
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-IQ1_S.gguf 5.98 GB 126a1ae1 download
Auxiliary files 3 files 116 MB
Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.imatrix.gguf 116 MB e2565800 download
.gitattributes 3.79 KB cec4fc01 download
README.md 1.67 KB bca2018f download

README current version from Hugging Face

license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated
tags:

  • gguf
  • uncensored
  • abliterated
  • code
  • moe
  • ollama

Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF — AI-conn fork

This is a fork, not our model. The abliterated weights are by
huihui-ai;
this GGUF conversion is by
mradermacher;
the base model is Qwen/Qwen3-Coder-30B-A3B-Instruct.
This fork exists so the fleet's copy cannot be altered or pulled upstream,
and to carry the fit notes below. License: Apache-2.0 (per the source repo).

Uncensored coder pick: MoE, 30B total / ~3B active per token — but note that
all expert weights must sit in VRAM for GPU residency; "3B active" does
not shrink the memory bill.

Recommended file for a 20 GB card: Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated.i1-Q4_K_M.gguf (17.28 GiB).

Ollama pull:

ollama pull hf.co/AI-conn/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated-i1-GGUF:i1-Q4_K_M

Prime fit (measured budget, RX 7900 XT — 19.98 GiB VRAM, 32 GB RAM)

  • i1-Q4_K_M 17.28 GiB + small MoE KV + ~0.7 GiB reserve ≈ 18.3 GiB —
    resident, tight
  • i1-IQ4_XS (15.24 GiB) is the roomy option if you want more context headroom
    at slightly lower quant fidelity.
  • Independent datapoint (community harness): the stock base scores 60.4% on
    HumanEval Pro. No independent coding eval of any abliterated build exists
    yet — our fleet settles coder rankings with a local bake-off, not cards.
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