community pool / model answer

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

code · unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

70.4 tok/s · model median · 10 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Arc Pro B70 32GB4-bit108.1 tok/sreported164- GB4,096llama.cpp
Radeon 890M 32GB4-bit30 tok/sreported1,500- GB2,048llama.cpp
Ryzen AI Max 385 24GB4-bit30 tok/sreported1,500- GB2,048llama.cpp
Ryzen AI Max 395 128GB4-bit70.3 tok/smeasured19118.8 GB65,536llama.cpp
Ryzen AI Max 395 64GB4-bit88.9 tok/smeasured79118.3 GB8,192llama.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.