community pool / model answer

LFM2.5-1.2B-Thinking-GGUF

chat · LiquidAI/LFM2.5-1.2B-Thinking-GGUF

128.2 tok/s · model median · 3 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit251.2 tok/sreported-3.6 GB128,000llama.cpp
RX 570 4GB4-bit114.6 tok/sreported79- GB2,048llama.cpp
RX 570 4GB ×24-bit128.2 tok/sreported18- 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.