community pool / model answer

BTL-3-Compact

chat · badtheorylabs/BTL-3-Compact

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M1 Max 64GB2-bit3.8 tok/sreported107,563- GB2,048llama.cpp, ollama

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.