community pool / model answer
Qwen3.8-Flash-Next-REAP-256-duo-GGUF
chat · AnonimousA/Qwen3.8-Flash-Next-REAP-256-duo-GGUF
53.6 tok/s · model median · 2 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB ×2 | 3-bit | 53.6 tok/s | reported | 2,949 | 33.9 GB | 32,768 | 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.