Qwen2.5 72B Instruct · 4× NVIDIA L40S · fp16

$/hr: $2.20
Weights / VRAM: 146 / 192 GB
FP16 TFLOPS: 1,448
HF repo: Qwen/Qwen2.5-72B-Instruct
Params: 72.7B · qwen2
Context: 131,072
License: qwen
Source: model: src · gpu: src

← all offerings · deployments