community pool / model answer
Qwythos-9B-Claude-Mythos-5-1M-GGUF
chat · empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF
53.6 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RX 7700 XT 12GB | 4-bit | 53.6 tok/s | reported | 197 | - GB | 2,048 | vllm |
| Ryzen AI Max 395 128GB | 4-bit | 35.3 tok/s | reported | 145 | 7.4 GB | 4,096 | llama.cpp |
| Ryzen AI Max 395 128GB | 5-bit | 22.3 tok/s | reported | 74,097 | 8.1 GB | 65,536 | 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.