community pool / model answer

Falcon-H1-0.5B-Instruct

chat · tiiuae/Falcon-H1-0.5B-Instruct

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
AMD Ryzen 7 7840HS2-bit136.6 tok/sreported-- GB2,048llama.cpp
AMD Ryzen 7 7840HS4-bit110.4 tok/sreported-- GB2,048llama.cpp
AMD Ryzen 7 7840HS8-bit78.2 tok/sreported-- 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.