community pool / model answer

Qwen3.5-122B-A10B-AWQ-4bit

chat · cyankiwi/Qwen3.5-122B-A10B-AWQ-4bit

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB ×44-bit123.1 tok/sreported12188.2 GB2,048vllm

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.