community pool / model answer

olmOCR-2-7B-1025-GGUF

chat · lmstudio-community/olmOCR-2-7B-1025-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Radeon 890M 32GB4-bit14.9 tok/sreported1,400- GB2,048llama.cpp
Ryzen AI Max 385 24GB4-bit14.9 tok/sreported1,400- 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.