What are the hardware requirements for Qwen3.5 122B A10B NVFP4?

Qwen3.5 122B A10B NVFP4 requires approximately 83.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 122B A10B NVFP4 and how large is it?

Qwen3.5 122B A10B NVFP4 is developed by nvidia, a model with 122b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen3.5 122B A10B NVFP4 perform on standard benchmarks?

Qwen3.5 122B A10B NVFP4 has the following published scores: LMSYS ELO 1417. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen3.5 122B A10B NVFP4 by nvidia — VRAM 83.5GB

Name: Qwen3.5 122B A10B NVFP4
Author: nvidia

Qwen3.5 122B A10B NVFP4 is an open-source language model by nvidia. Features: 122b LLM, VRAM: 83.5GB, License: apache-2.0, LLM Explorer Score: 0.5, ELO: 1417.

8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-122b-a... Conversational Deploy:azure Fp4 Model optimizer Modelopt Nvfp4 Nvidia Quantized Qwen3.5 Qwen3 5 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nvidia/Qwen3.5-122B-A10B-NVFP4

Qwen3.5 122B A10B NVFP4 Benchmarks

LMSys ELO 1417 vs 1272 (so35) 11.4%

^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)

Qwen3.5 122B A10B NVFP4 Parameters and Internals

LLM Name	Qwen3.5 122B A10B NVFP4
Repository 🤗	https://huggingface.co/nvidia/Qwen3.5-122B-A10B-NVFP4
Base Model(s)	Qwen/Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B
Model Size	122b
Required VRAM	83.5 GB
Updated	2026-08-05
Maintainer	nvidia
Model Type	qwen3_5_moe
Model Files	10.0 GB: 1-of-9 10.0 GB: 2-of-9 10.0 GB: 3-of-9 10.0 GB: 4-of-9 10.0 GB: 5-of-9 10.0 GB: 6-of-9 10.0 GB: 7-of-9 10.0 GB: 8-of-9 3.5 GB: 9-of-9
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.6.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.5 122B A10B NVFP4 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 Qwen3.5 122B A10B NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 122B A10B	0K / 248.6 GB	2139628	605
Qwen3.5 122B A10B	0K / 248.6 GB	45	1
Qwen3.5 122B A10B	0K / 248.6 GB	1680	8
Qwen3.5 122B A10B Abliterated	0K / 248.6 GB	59	5
Qwen3.5 122B A10B FP8	0K / 126.3 GB	1271983	112
Qwen3.5 122B A10B NVFP4	0K / 74 GB	18267	18
...en3.5 122B A10B Int4 AutoRound	0K / 72 GB	142311	45
AREX Base	0K / 164.2 GB	571	21
Qwen3.5 122B A10B WMix48	0K / 73.2 GB	215	3
Qwen3.5 122B A10B WMix58	0K / 87.5 GB	214	3