gpt-oss 120B · 8× NVIDIA GeForce RTX 4090 · fp8

$/hr: $2.80
Weights / VRAM: 117 / 192 GB
FP16 TFLOPS: 1,320
Params: 117.0B · gpt_oss
Context: 131,072
License: apache-2.0

← all offerings · deployments