What are the hardware requirements for Agnes 3.0 Qwen?

Agnes 3.0 Qwen requires approximately 155.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Agnes 3.0 Qwen and how large is it?

Agnes 3.0 Qwen is developed by Agnes-AI, a model with 180b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Agnes 3.0 Qwen?

Agnes 3.0 Qwen is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Agnes 3.0 Qwen by Agnes-AI — VRAM 155.9GB

Name: Agnes 3.0 Qwen
Author: Agnes-AI

Agnes 3.0 Qwen is an open-source language model by Agnes-AI. Features: 180b LLM, VRAM: 155.9GB, License: other, LLM Explorer Score: 0.33.

Agentic Agnes-ai Api Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.8-flash-... Conversational En Image-text-to-text Long-context Multimodal Qwen4 exp Reasoning Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/Agnes-AI/Agnes-3.0-Qwen

Agnes 3.0 Qwen Parameters and Internals

LLM Name	Agnes 3.0 Qwen
Repository 🤗	https://huggingface.co/Agnes-AI/Agnes-3.0-Qwen
Base Model(s)	Qwen/Qwen3.8-Flash-Next Qwen/Qwen3.8-Flash-Next
Model Size	180b
Required VRAM	155.9 GB
Updated	2026-10-14
Maintainer	Agnes-AI
Model Type	qwen4_exp
Model Files	4.8 GB: 1-of-119 1.8 GB: 2-of-119 3.4 GB: 3-of-119 4.9 GB: 4-of-119 4.8 GB: 5-of-119 4.8 GB: 6-of-119 4.8 GB: 7-of-119 4.8 GB: 8-of-119 4.8 GB: 9-of-119 4.8 GB: 10-of-119 4.8 GB: 11-of-119 4.8 GB: 12-of-119 4.8 GB: 13-of-119 4.8 GB: 14-of-119 4.8 GB: 15-of-119 4.8 GB: 16-of-119 4.8 GB: 17-of-119 4.8 GB: 18-of-119 4.8 GB: 19-of-119 4.8 GB: 20-of-119 4.8 GB: 21-of-119 4.8 GB: 22-of-119 4.8 GB: 23-of-119 4.8 GB: 24-of-119 3.4 GB: 25-of-119 3.4 GB: 26-of-119 1.8 GB: 27-of-119 3.4 GB: 28-of-119 1.8 GB: 29-of-119 3.4 GB: 30-of-119 1.8 GB: 31-of-119 3.4 GB: 32-of-119 1.8 GB: 33-of-119 3.4 GB: 34-of-119 1.8 GB: 35-of-119 3.4 GB: 36-of-119 1.8 GB: 37-of-119 3.4 GB: 38-of-119 1.8 GB: 39-of-119 3.4 GB: 40-of-119 1.8 GB: 41-of-119
Supported Languages	en zh
Model Architecture	Qwen4ExpForConditionalGeneration
License	other
Transformers Version	5.8.0.dev0

Rank the Agnes 3.0 Qwen 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 Agnes 3.0 Qwen

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 Flash Next	0K / 129.5 GB	4810	3918
Darwin 180B RSI	0K / 119 GB	353	94
Qwen3.8 Flash Next OQ4e Mtp	0K / 106.4 GB	21637	86
CYBER FROST 3.8 BF16	0K / 124.3 GB	1824	63
...Qwen3.8 Flash Next Abliterated	0K / 129.5 GB	493	42
Qwen3.8 Flash Next FP8	0K / 65.7 GB	2219	117
Tinfield 1	0K / 129.5 GB	577	41
Qwen3.8 Flash Next W4A16	0K / 0.5 GB	6043	22
Qwen3.8 Flash Next NVFP4	0K / 180.8 GB	1503	35
Darwin 180B RSI R3	0K / 127.7 GB	151	7

Note: green Score (e.g. "73.2") means that the model is better than Agnes-AI/Agnes-3.0-Qwen.