community pool / model answer

Qwen3.8-Flash-Next-REAP-256-duo-GGUF

chat · AnonimousA/Qwen3.8-Flash-Next-REAP-256-duo-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB ×23-bit53.6 tok/sreported2,94933.9 GB32,768llama.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.