community pool / model answer

MiniCPM5-1B-GGUF

chat · openbmb/MiniCPM5-1B-GGUF

97.6 tok/s · model median · 32 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit125.9 tok/sreported-4.3 GB128,000llama.cpp
RX 570 4GB4-bit102.8 tok/smeasured27- GB2,048llama.cpp
RX 570 4GB ×24-bit70 tok/smeasured47- GB2,048llama.cpp
RX 5700 8GB4-bit221.6 tok/sreported16- 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.