community pool / model answer

Qwen3-30B-A3B-Instruct-2507-GGUF

chat · unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Arc Pro B70 32GB4-bit107.5 tok/sreported167- 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.