community pool / model answer

Qwen3.8-27B-GGUF

chat · ggml-org/Qwen3.8-27B-GGUF

44.6 tok/s · model median · 4 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Arc Pro B70 32GB4-bit27.8 tok/sreported255- GB8,192llama.cpp
Arc Pro B70 32GB ×24-bit45.9 tok/smeasured174- 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.