nvidia / image-text-to-text updated 4 months ago

Cosmos-Reason2-2B

Params
2.4 B
Context
Downloads 30d
840 K
Likes
224
Licence: other Gated — accept licence SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 32 days
▲ 15 K in the last 30 days (1.8%)
995 K831 K
Aug 21Aug 31Sep 11Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 4.9 GB 6.2 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
Qwen3VLForConditionalGeneration
Parameters
2.4 B
Tensor type
BF16
Licence
other
First seen on the Hub
2025-12-12
Base model
Qwen3-VL-2B-Instruct
Training datasets
undisclosed
Added to our catalog
2026-08-21

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any image-text-to-text model