community pool / model answer

Qwen3.8-27B-nvfp4-NInfer

chat · neroued/Qwen3.8-27B-nvfp4-NInfer

231.8 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5090 32GB4-bit231.8 tok/sreported15623.2 GB16,384tensorrt-llm

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.