community pool / model answer

Qwen3.5-0.8B-Q8_0.gguf

chat · Manojb/Qwen3.5-0.8B-Q8_0.gguf

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RX 7900 XTX 24GB8-bit346.2 tok/sreported-1.1 GB512llama.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.