community pool / model answer

Qwen3.5-0.8B

chat · unsloth/Qwen3.5-0.8B

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RX 6700 10GB4-bit125.9 tok/sreported2,1234 GB4,096llama.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.