Qwen3-35B-A3B

3 records across 1 hardware.

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
2× NVIDIA RTX A5000 24 GBQwen3-35B-A3B FP8vLLM145.3––––2026-09-27community–source
2× NVIDIA RTX A5000 24 GBQwen3-35B-A3B FP8vLLM48.6–––1638402026-09-27community–source
2× NVIDIA RTX A5000 24 GBQwen3-35B-A3B FP8vLLM11––––2026-09-27community–source

← all models