Downloads · 30 days
59
32% of all-time downloads
cosmos-reason2-2b-fp8-hf
cagataydev/cosmos-reason2-2b-fp8-hf
cosmos-reason2-2b-fp8-hf is a image-text-to-text model from cagataydev. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
Source: nvidia/Cosmos-Reason2-2B (Qwen3-VL) Quantization: FP8 on languagemodel (vision tower bf16) Toolchain: NVIDIA ModelOpt 0.43.0 exporthfcheckpoint Calibration: 8 multimodal (image+text) samples
All-time downloads
183
Public
Parameters
2.1B
2.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.8 GB · 99%
Parameter types
How the weights are stored.
F8_E4M31.4B · 66%
Try a prompt
Base models
Model card
From the Hugging Face model README
Cosmos-Reason2-2B FP8 (HF checkpoint via ModelOpt)
Source: nvidia/Cosmos-Reason2-2B (Qwen3-VL) Quantization: FP8 on language_model (vision tower bf16) Toolchain: NVIDIA ModelOpt 0.43.0 export_hf_checkpoint Calibration: 8 multimodal (image+text) samples
For TensorRT-LLM / TensorRT-Edge-LLM engine build on Jetson Thor, this
checkpoint is the input to trtllm-build --model_dir <this>.
Provenance
- AWS EC2 NVIDIA L40S, Ubuntu 24.04
- torch==2.6.0+cu124, transformers==4.57.6, nvidia-modelopt==0.43.0, tensorrt==10.16.1
- Produced by DevDuck auto-pipeline 2026-05-07
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- License
- other
- Created
- May 7, 2026
- Updated
- May 7, 2026