community pool / model answer

Qwen3.8-27B-ABLITERATED-GGUF

chat · Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF

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

Answer

17.3tok/s

reportedM5 Max 128GB8-bit · 1 run · decodebest cell in the pool

  1. M5 Max 128GB · unified memory17.3 tok/sreported1 run · peak VRAM no data yet
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
M5 Max 128GB8-bit17.3 tok/sreported329- GB2,048llama.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.