community pool / model answer

Laguna-S-2.1-GGUF

chat · unsloth/Laguna-S-2.1-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB ×24-bit43.6 tok/sreported640- GB2,048llama.cpp
Ryzen AI Max 395 64GB3-bit32.6 tok/sreported3,32551.9 GB8,192llama.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.