community pool / model answer

Qwen3-14B-GGUF

chat · unsloth/Qwen3-14B-GGUF

34.8 tok/s · model median · 19 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB ×24-bit29.7 tok/smeasured3,77615.4 GB131,072llama.cpp
RTX 3090 24GB4-bit44.4 tok/smeasured2,655- GB131,072llama.cpp
RTX 5070 12GB4-bit66.6 tok/sreported186- 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.