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 rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B70 32GB | 4-bit | 108.1 tok/s | reported | 164 | - GB | 4,096 | llama.cpp |
| Radeon 890M 32GB | 4-bit | 30 tok/s | reported | 1,500 | - GB | 2,048 | llama.cpp |
| Ryzen AI Max 385 24GB | 4-bit | 30 tok/s | reported | 1,500 | - GB | 2,048 | llama.cpp |
| Ryzen AI Max 395 128GB | 4-bit | 70.3 tok/s | measured | 191 | 18.8 GB | 65,536 | llama.cpp |
| Ryzen AI Max 395 64GB | 4-bit | 88.9 tok/s | measured | 791 | 18.3 GB | 8,192 | llama.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.