What are the hardware requirements for Qwen3 235B A22B Thinking 2507 Eagle3?

Qwen3 235B A22B Thinking 2507 Eagle3 requires approximately 0.6 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 235B A22B Thinking 2507 Eagle3 and how large is it?

Qwen3 235B A22B Thinking 2507 Eagle3 is developed by nvidia, a model with 235b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen3 235B A22B Thinking 2507 Eagle3 perform on standard benchmarks?

Qwen3 235B A22B Thinking 2507 Eagle3 has the following published scores: LMSYS ELO 1399. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen3 235B A22B Thinking 2507 Eagle3 by nvidia — VRAM 0.6GB, 256K context

Name: Qwen3 235B A22B Thinking 2507 Eagle3
Author: nvidia

Qwen3 235B A22B Thinking 2507 Eagle3 is an open-source language model by nvidia. Features: 235b LLM, VRAM: 0.6GB, Context: 256K, License: other, LLM Explorer Score: 0.34, ELO: 1399.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-235b-a22... Eagle3 Llama Model optimizer Modelopt Nvidia Qwen3-235b-a22b-thinking-2507 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/nvidia/Qwen3-235B-A22B-Thinking-2507-Eagle3

Qwen3 235B A22B Thinking 2507 Eagle3 Benchmarks

LMSys ELO 1399 vs 1272 (so35) 10%

^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 235B A22B Thinking 2507 Eagle3 Parameters and Internals

LLM Name	Qwen3 235B A22B Thinking 2507 Eagle3
Repository 🤗	https://huggingface.co/nvidia/Qwen3-235B-A22B-Thinking-2507-Eagle3
Base Model(s)	Qwen3 235B A22B Thinking 2507 Qwen/Qwen3-235B-A22B-Thinking-2507
Model Size	235b
Required VRAM	0.6 GB
Updated	2026-07-27
Maintainer	nvidia
Model Type	llama
Model Files	0.6 GB
Model Architecture	LlamaForCausalLMEagle3
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	4.55.2
Vocabulary Size	151936
Torch Data Type	bfloat16

Rank the Qwen3 235B A22B Thinking 2507 Eagle3 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 235B A22B Thinking 2507 Eagle3

Best Alternatives	Context / RAM	Downloads	Likes
... A22B Thinking 2507 FP4 Eagle3	256K / 1.8 GB	94	1
Qwen3 235B A22B Eagle3	40K / 0.6 GB	314	13