Qwen2.5 7B Instruct · 1× NVIDIA GeForce RTX 4090 · fp8

$/hr: $0.35
Weights / VRAM: 8 / 24 GB
FP16 TFLOPS: 165
Params: 7.6B · qwen2
Context: 131,072
License: apache-2.0

← all offerings · deployments