community pool / model answer

Laguna-S-2.1-IQ4_XS-Q4_K_M-GGUF

chat · Abiray/Laguna-S-2.1-IQ4_XS-Q4_K_M-GGUF

68.1 tok/s · model median · 4 runs in the model record.

Answer

68.1tok/s

measuredCMP 170HX 64GB ×24-bit · 4 runs · decodebest cell in the pool

  1. CMP 170HX 64GB ×268.1 tok/smeasured4 runs · peak 71.7 GB · fits 128 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
CMP 170HX 64GB ×24-bit68.1 tok/smeasured-71.7 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.