LLM EXPLORER 60,783 MODELS INDEXED

Qwen3 235B A22B Instruct 2507 by unsloth

By unsloth · 28 downloads
HF Repo ↗ Copy URL

Qwen3 235B A22B Instruct 2507 is an open-source language model by unsloth. Features: 235b LLM, VRAM: 167.9GB, Context: 256K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.33, ELO: 1423.

  Arxiv:2505.09388 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-235b-a22...   Conversational   Endpoints compatible   Instruct   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507 

Qwen3 235B A22B Instruct 2507 Benchmarks

LMSys ELO 1423 vs 1272 (so35) 11.9%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen3 235B A22B Instruct 2507 Parameters and Internals

LLM NameQwen3 235B A22B Instruct 2507
Repository 🤗https://huggingface.co/unsloth/Qwen3-235B-A22B-Instruct-2507 
Base Model(s)  Qwen3 235B A22B Instruct 2507   Qwen/Qwen3-235B-A22B-Instruct-2507
Model Size235b
Required VRAM167.9 GB
Updated2026-08-04
Maintainerunsloth
Model Typeqwen3_moe
Instruction-BasedYes
Model Files  4.0 GB: 1-of-118   4.0 GB: 2-of-118   4.0 GB: 3-of-118   4.0 GB: 4-of-118   4.0 GB: 5-of-118   4.0 GB: 6-of-118   4.0 GB: 7-of-118   4.0 GB: 8-of-118   4.0 GB: 9-of-118   4.0 GB: 10-of-118   4.0 GB: 11-of-118   4.0 GB: 12-of-118   4.0 GB: 13-of-118   4.0 GB: 14-of-118   4.0 GB: 15-of-118   4.0 GB: 16-of-118   4.0 GB: 17-of-118   4.0 GB: 18-of-118   4.0 GB: 19-of-118   4.0 GB: 20-of-118   4.0 GB: 21-of-118   4.0 GB: 22-of-118   4.0 GB: 23-of-118   3.9 GB: 24-of-118   4.0 GB: 25-of-118   4.0 GB: 26-of-118   4.0 GB: 27-of-118   4.0 GB: 28-of-118   4.0 GB: 29-of-118   4.0 GB: 30-of-118   4.0 GB: 31-of-118   4.0 GB: 32-of-118   4.0 GB: 33-of-118   4.0 GB: 34-of-118   4.0 GB: 35-of-118   4.0 GB: 36-of-118   4.0 GB: 37-of-118   4.0 GB: 38-of-118   4.0 GB: 39-of-118   4.0 GB: 40-of-118   4.0 GB: 41-of-118   4.0 GB: 42-of-118
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.54.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 235B A22B Instruct 2507

Best Alternatives
Context / RAM
Downloads
Likes
...en3 235B A22B Instruct 2507 1M986K / 171.9 GB41
Qwen3 235B A22B Instruct 2507256K / 171.9 GB59472793
Vivo C V1256K / 156.4 GB4152
... 235B A22B Instruct 2507 NVFP4256K / 139.2 GB1432210
...n3 235B A22B Instruct 2507 FP8256K / 236.5 GB54126147
... 235B A22B Instruct 2507 MXFP4256K / 126.8 GB17632
...n3 235B A22B Instruct 2507 FP8256K / 236.5 GB1283
...3 235B A22B Instruct 2507 4bit256K / 131.4 GB26583
...3 235B A22B Instruct 2507 8bit256K / 227.7 GB25912
...5B A22B Instruct 2507 3bit DWQ256K / 103 GB1745