What are the hardware requirements for Qwen3.6 35B A3B Abliterated V2?

Qwen3.6 35B A3B Abliterated V2 requires approximately 70.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 35B A3B Abliterated V2 and how large is it?

Qwen3.6 35B A3B Abliterated V2 is developed by wangzhang, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen3.6 35B A3B Abliterated V2 perform on standard benchmarks?

Qwen3.6 35B A3B Abliterated V2 has the following published scores: LMSYS ELO 1396. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen3.6 35B A3B Abliterated V2 by wangzhang — VRAM 70.2GB

Name: Qwen3.6 35B A3B Abliterated V2
Author: wangzhang

Qwen3.6 35B A3B Abliterated V2 is an open-source language model by wangzhang. Features: 35b LLM, VRAM: 70.2GB, License: other, LLM Explorer Score: 0.4, ELO: 1396.

Abliterated Abliterix Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.6-35b-a3... Moe Qwen3 Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Uncensored

Model Card on HF 🤗: https://huggingface.co/wangzhang/Qwen3.6-35B-A3B-abliterated-v2

Qwen3.6 35B A3B Abliterated V2 Benchmarks

LMSys ELO 1396 vs 1272 (so35) 9.7%

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

What is the LLM Explorer Rank (Score)

Qwen3.6 35B A3B Abliterated V2 Parameters and Internals

LLM Name	Qwen3.6 35B A3B Abliterated V2
Repository 🤗	https://huggingface.co/wangzhang/Qwen3.6-35B-A3B-abliterated-v2
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	70.2 GB
Updated	2026-07-18
Maintainer	wangzhang
Model Type	qwen3_5_moe
Model Files	49.7 GB: 1-of-2 20.5 GB: 2-of-2
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	other
Model Max Length	262144
Transformers Version	5.5.4
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.6 35B A3B Abliterated V2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Qwen3.6 35B A3B Abliterated V2

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
KAT Coder V2.5 Dev	0K / 69.7 GB	17885	537
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
XYZ Aquila Mini	0K / 70.2 GB	1760	432
BTL 4	0K / 69.9 GB	571	74
Qwen3.6 35B A3B Escha W2	0K / 12.3 GB	3622	236
BigBang V1	0K / 71.5 GB	154	84
...e 4.7 Opus Reasoning Distilled	0K / 72.2 GB	28687	194
GRM 3.2 Sky	0K / 70.4 GB	717	31
Ornith 1.0 35B MTPLX	0K / 19.5 GB	25034	18

Note: green Score (e.g. "73.2") means that the model is better than wangzhang/Qwen3.6-35B-A3B-abliterated-v2.