HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Cosmos-Reason2-32B

nvidia/Cosmos-Reason2-32B

kind
original
quant
bf16 (16-bit)
family
misc
modality
image-text-to-text
root model
Qwen/Qwen3-VL-32B-Instruct
provider
nvidia
license
other
language
—
context
—
library
cosmos
vRAM (GB)
—
size on disk
—
downloads
3,686
likes
14
created
—
last modified
2026-04-30T01:18:56+00:00 (2026)
huggingface
https://huggingface.co/nvidia/Cosmos-Reason2-32B
tags
cosmossafetensorsqwen3_vlnvidiaconversationalimage-text-to-textarxiv:2503.06800arxiv:2406.10721arxiv:2603.18178arxiv:2312.14115base_model:Qwen/Qwen3-VL-32B-Instructbase_model:finetune:Qwen/Qwen3-VL-32B-Instructlicense:otherregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.