community pool / model answer

Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP

chat · rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP

195.4 tok/s · model median · 38 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5090 32GB4-bit195.4 tok/smeasured1,220- GB262,144vllm

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.