community pool / model answer

Qwen3.8-4B-Distill-GGUF

chat · empero-ai/Qwen3.8-4B-Distill-GGUF

97.1 tok/s · model median · 1 runs in the model record.

Answer

97.1tok/s

reportedRTX 2060 Super 8GB4-bit · 1 run · decodebest cell in the pool

  1. RTX 2060 Super 8GB97.1 tok/sreported1 run · peak 3 GB · fits 8 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 2060 Super 8GB4-bit97.1 tok/sreported-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.