community pool / model answer

Qwen3-1.7B

chat · Qwen/Qwen3-1.7B

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M3 Ultra 512GB4-bit213 tok/sreported24- GB8,192llama.cpp
RTX 3060 12GB8-bit147.7 tok/sreported5484 GB4,608llama.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.