HF Model & Benchmark Matrix

Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.1-FP8-KV

nvidia/Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.1-FP8-KV

kind

nvfp4

quant

nvfp4 (4-bit)

family

qwen

modality

—

root model

Qwen/Qwen3-VL-235B-A22B-Instruct

provider

nvidia

license

—

language

—

context

—

library

—

vRAM (GB)

—

size on disk

—

downloads

335,330

likes

2

created

—

last modified

2026-06-17T18:55:25+00:00 (2026)

huggingface

https://huggingface.co/nvidia/Qwen3-VL-235B-A22B-Instruct-NVFP4-MLPerf-Inference-Closed-V6.1-FP8-KV

tags

safetensorsqwen3_vl_moe8-bitmodeloptregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.