llmfan46 / Model details

Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF

llmfan46/Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF

abliterateduncensoredfine-tuned

Read the original model card ↗ · Choosing a model

About this model

llmfan46's GGUF release derived from Qwen/Qwen3.5-122B-A10B, which the model card describes as a decensored version made using Heretic. The creator says all 785 MTP components are preserved, and the repository includes a BF16 vision projector file required for vision or multimodal use. According to the model card, refusals drop from 92/100 in the original to 8/100 here, with a KL divergence of 0.0856 presented as evidence of reduced censorship while staying close to the original. Weights are provided as GGUF quantizations from BF16 down to Q2_K under the Apache-2.0 license. These refusal and quality claims have not been independently tested.

Description sources

https://huggingface.co/llmfan46/Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF/raw/5d7ec1c1d8b53d35f2d6ee3bb7c900b9ba4004b1/README.md ↗

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model: Qwen/Qwen3.5-122B-A10B
Parameters: Unknown
Main repository formats: GGUF
License tag: apache-2.0
Languages: Unknown
Last updated: 2026-08-30 · 09:54:19.000 UTC

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

abliteratedsource tag: abliterated
uncensoredsource tag: uncensored
uncensoredmodel name: Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF
fine-tunedsource tag: base_model:finetune:Qwen/Qwen3.5-122B-A10B

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

Qwen: Base model: Qwen/Qwen3.5-122B-A10B

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Main repository files ↗GGUF
No other explicitly linked versions recorded.

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/llmfan46-qwen3-5-122b-a10b-uncensored-heretic-native-mtp-preserved-gguf/)

HTML

<a href="https://customclankers.com/models/llmfan46-qwen3-5-122b-a10b-uncensored-heretic-native-mtp-preserved-gguf/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Tools to customize it further

Make a smaller download (quantize)

llama.cpp ↗ ★ 132,860
Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.

Learn the techniques

LLM Course ↗ ★ 84,792
A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads: 35,904
Likes: 8
Metadata checked: 2026-10-31 · 12:11:03 UTC
First seen in index: 2026-10-31 · 12:11:03 UTC
Source revision: 5d7ec1c1d8b53d35f2d6ee3bb7c900b9ba4004b1

Source-card excerpt

Source model card excerpt: 🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨 I can no longer upload new models unless I can cover the cost of

From llmfan46/Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗