community pool / model answer

Qwen3.5-4B-GGUF

chat · unsloth/Qwen3.5-4B-GGUF

50.4 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3060 12GB4-bit78.6 tok/sreported-3.5 GB32,768llama.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.