community pool / model answer

Qwen3.8-27B-ATX-IQ4_XS-M-GGUF

chat · jakeatx/Qwen3.8-27B-ATX-IQ4_XS-M-GGUF

107.9 tok/s · model median · 1 runs in the model record.

Answer

107.9tok/s

reportedRTX 3090 Ti 24GB4-bit · 1 run · decodebest cell in the pool

  1. RTX 3090 Ti 24GB107.9 tok/sreported1 run · peak VRAM no data yet · 24 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 Ti 24GB4-bit107.9 tok/sreported-- GB112,640llama.cpp

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.