LLM EXPLORER 58,297 MODELS INDEXED

Qwen3 30B A3B Abliterated by mlabonne

By mlabonne · 437852 downloads
HF Repo ↗ Copy URL

Qwen3 30B A3B Abliterated is an open-source language model by mlabonne. Features: 30b LLM, VRAM: 183.3GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.27.

  Abliterated   Abliteration Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-30b-a3b   Conversational   Endpoints compatible   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/Qwen3-30B-A3B-abliterated 

Qwen3 30B A3B Abliterated Parameters and Internals

LLM NameQwen3 30B A3B Abliterated
Repository 🤗https://huggingface.co/mlabonne/Qwen3-30B-A3B-abliterated 
Base Model(s)  Qwen3 30B A3B   Qwen/Qwen3-30B-A3B
Model Size30b
Required VRAM183.3 GB
Updated2026-08-08
Maintainermlabonne
Model Typeqwen3_moe
Model Files  5.0 GB: 1-of-13   5.0 GB: 1-of-25   5.0 GB: 2-of-13   5.0 GB: 2-of-25   5.0 GB: 3-of-13   5.0 GB: 3-of-25   5.0 GB: 4-of-13   5.0 GB: 4-of-25   5.0 GB: 5-of-13   5.0 GB: 5-of-25   5.0 GB: 6-of-13   5.0 GB: 6-of-25   5.0 GB: 7-of-13   5.0 GB: 7-of-25   5.0 GB: 8-of-13   5.0 GB: 8-of-25   5.0 GB: 9-of-13   5.0 GB: 9-of-25   5.0 GB: 10-of-13   5.0 GB: 10-of-25   5.0 GB: 11-of-13   5.0 GB: 11-of-25   5.0 GB: 12-of-13   5.0 GB: 12-of-25   1.1 GB: 13-of-13   5.0 GB: 13-of-25   5.0 GB: 14-of-25   5.0 GB: 15-of-25   5.0 GB: 16-of-25   5.0 GB: 17-of-25   5.0 GB: 18-of-25   5.0 GB: 19-of-25   5.0 GB: 20-of-25   5.0 GB: 21-of-25   5.0 GB: 22-of-25   5.0 GB: 23-of-25   5.0 GB: 24-of-25   2.2 GB: 25-of-25
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Qwen3 30B A3B Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
...LL MASTER CODER M 1million Ctx1024K / 84.8 GB1539
... 42B A3B Thinking Total Recall986K / 84.8 GB260
Qwen3 30B A3B YOYO V3986K / 61.1 GB117
...07 YOYO2 TOTAL RECALL Instruct986K / 84.8 GB271
...07 YOYO2 TOTAL RECALL Instruct986K / 106 GB200
Qwen3 30B A3B YOYO V2986K / 61.1 GB194
Qwen3 Coder 30B A3B Instruct256K / 61.1 GB17467711168
Qwen3 30B A3B Instruct 2507256K / 61.1 GB393713
Qwen3 30B A3B Instruct 2507256K / 61.1 GB1903736824
...en3 Coder 30B A3B Instruct FP8256K / 31.2 GB1556690191
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/Qwen3-30B-A3B-abliterated.