community pool / model answer

Qwen3-Coder-30B-A3B-Instruct-GGUF

code · lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Radeon RX 7900 XTX 24GB4-bit46.9 tok/sreported-- GB1,024llama.cpp
RTX 5090 32GB6-bit263 tok/sreported25- GB2,048lmstudio

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.