Qwen3 235B-A22B Instruct 2507 · 8× NVIDIA L40S · fp8

$/hr
$4.40
Weights / VRAM
235 / 384 GB
FP16 TFLOPS
2,896
HF repo
Qwen/Qwen3-235B-A22B-Instruct-2507
Params
235.0B · qwen3_moe
Context
262,144
License
apache-2.0
Source
model: src · gpu: src

← all offerings · deployments