SamTheDev
/

Qwen3-1.7B-oga

Text Generation

onnxruntime-genai

Model card Files Files and versions Community

My Tests (Tesla P4)

CUDA int4: 2179 MiB, 6 TPS
CUDA fp16: 4221 MiB, 21 TPS
CUDA fp32: dnf (memory)

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Text Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SamTheDev/Qwen3-1.7B-oga

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Quantized

(89)

this model

Collection including SamTheDev/Qwen3-1.7B-oga

Onnxruntime-Genai Models

onnxruntime-genai models that i've tested on the nvidia tesla p4 • 2 items • Updated 19 days ago