LLM EXPLORER 60,783 MODELS INDEXED

Qwen3.5 122B A10B Abliterated by Chompa1422

By Chompa1422 · 59 downloads
HF Repo ↗ Copy URL

Qwen3.5 122B A10B Abliterated is an open-source language model by Chompa1422. Features: 122b LLM, VRAM: 248.6GB, License: apache-2.0, LLM Explorer Score: 0.37, ELO: 1417.

  Abliterated Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-122b-a...   Conversational   En   Moe   Pentest   Qwen3.5   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Uncensored
Model Card on HF 🤗: https://huggingface.co/Chompa1422/Qwen3.5-122B-A10B-abliterated 

Qwen3.5 122B A10B Abliterated Benchmarks

LMSys ELO 1417 vs 1272 (so35) 11.4%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen3.5 122B A10B Abliterated Parameters and Internals

LLM NameQwen3.5 122B A10B Abliterated
Repository 🤗https://huggingface.co/Chompa1422/Qwen3.5-122B-A10B-abliterated 
Base Model(s)  Qwen/Qwen3.5-122B-A10B   Qwen/Qwen3.5-122B-A10B
Model Size122b
Required VRAM248.6 GB
Updated2026-09-10
MaintainerChompa1422
Model Typeqwen3_5_moe
Model Files  6.4 GB: 1-of-39   6.4 GB: 2-of-39   6.4 GB: 3-of-39   6.4 GB: 4-of-39   6.4 GB: 5-of-39   6.4 GB: 6-of-39   6.4 GB: 7-of-39   6.4 GB: 8-of-39   6.4 GB: 9-of-39   6.4 GB: 10-of-39   6.4 GB: 11-of-39   6.4 GB: 12-of-39   6.4 GB: 13-of-39   6.4 GB: 14-of-39   6.4 GB: 15-of-39   6.4 GB: 16-of-39   6.4 GB: 17-of-39   6.4 GB: 18-of-39   6.4 GB: 19-of-39   6.4 GB: 20-of-39   6.4 GB: 21-of-39   6.4 GB: 22-of-39   6.4 GB: 23-of-39   6.4 GB: 24-of-39   6.4 GB: 25-of-39   6.4 GB: 26-of-39   6.4 GB: 27-of-39   6.4 GB: 28-of-39   6.4 GB: 29-of-39   6.4 GB: 30-of-39   6.4 GB: 31-of-39   6.4 GB: 32-of-39   6.4 GB: 33-of-39   6.4 GB: 34-of-39   6.4 GB: 35-of-39   6.4 GB: 36-of-39   6.4 GB: 37-of-39   6.4 GB: 38-of-39   5.4 GB: 39-of-39
Supported Languagesen
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 122B A10B Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 122B A10B NVFP40K / 83.5 GB24873249
Qwen3.5 122B A10B0K / 248.6 GB2139628605
Qwen3.5 122B A10B0K / 248.6 GB451
Qwen3.5 122B A10B0K / 248.6 GB16808
Qwen3.5 122B A10B FP80K / 126.3 GB1271983112
Qwen3.5 122B A10B NVFP40K / 74 GB1826718
...en3.5 122B A10B Int4 AutoRound0K / 72 GB14231145
AREX Base0K / 164.2 GB57121
Qwen3.5 122B A10B WMix480K / 73.2 GB2153
Qwen3.5 122B A10B WMix580K / 87.5 GB2143
Note: green Score (e.g. "73.2") means that the model is better than Chompa1422/Qwen3.5-122B-A10B-abliterated.