community pool / model answer

Agents-A1-4B-Q4_K_M-GGUF

chat · InternScience/Agents-A1-4B-Q4_K_M-GGUF

76.6 tok/s · model median · 11 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit76.6 tok/smeasured1,132- GB131,072llama.cpp
RX 7700 XT 12GB4-bit77.7 tok/sreported99- GB2,048vllm

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.