community pool / model answer

Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4

chat · AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4

33.5 tok/s · model median · 7 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
GB10 Grace Blackwell 128GB4-bit33.5 tok/smeasured13,000108 GB256,000vllm
RTX 5090 32GB4-bit56.7 tok/smeasured-- GB65,536vllm

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.