community pool / model answer

Qwen3-1.7B-GGUF

chat · Qwen/Qwen3-1.7B-GGUF

116 tok/s · model median · 29 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit96.2 tok/smeasured109- GB131,072llama.cpp
RTX 3060 12GB ×24-bit112.6 tok/smeasured7376.7 GB131,072llama.cpp
RTX 3060 Ti 8GB4-bit116 tok/smeasured2325.8 GB131,072llama.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.