community pool / model answer

Qwen3.8-27B-GGUF

chat · AtomicChat/Qwen3.8-27B-GGUF

46.1 tok/s · model median · 3 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5070 12GB2-bit46 tok/sreported54410.1 GB2,048llama.cpp
RTX 5090 32GB6-bit98.7 tok/sreported27929.4 GB131,000llama.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.