community pool / model answer

gpt-oss-120b-GGUF

chat · unsloth/gpt-oss-120b-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz6-bit12.4 tok/sreported524- GB2,048llama.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.