LLM EXPLORER 58,608 MODELS INDEXED

Qwen3 235B A22B Eagle3 by nvidia

By nvidia · 314 downloads
HF Repo ↗ Copy URL

Qwen3 235B A22B Eagle3 is an open-source language model by nvidia. Features: 235b LLM, VRAM: 0.6GB, Context: 40K, License: other, LLM Explorer Score: 0.34, ELO: 1375.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-235b-a22...   Eagle3   Llama   Model optimizer   Modelopt   Nvidia   Quantized   Qwen3-235b-a22b   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/nvidia/Qwen3-235B-A22B-Eagle3 

Qwen3 235B A22B Eagle3 Benchmarks

LMSys ELO 1375 vs 1272 (so35) 8.1%
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 Eagle3 Parameters and Internals

LLM NameQwen3 235B A22B Eagle3
Repository 🤗https://huggingface.co/nvidia/Qwen3-235B-A22B-Eagle3 
Base Model(s)  Qwen3 235B A22B   Qwen/Qwen3-235B-A22B
Model Size235b
Required VRAM0.6 GB
Updated2026-08-08
Maintainernvidia
Model Typellama
Model Files  0.6 GB
Model ArchitectureLlamaForCausalLMEagle3
Licenseother
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to Qwen3 235B A22B Eagle3

Best Alternatives
Context / RAM
Downloads
Likes
...235B A22B Thinking 2507 Eagle3256K / 0.6 GB1012
... A22B Thinking 2507 FP4 Eagle3256K / 1.8 GB941
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Qwen3-235B-A22B-Eagle3.