community pool / model answer

Qwen3.6-35B-A3B-abliterated-v4-GGUF

chat · Bahushruth/Qwen3.6-35B-A3B-abliterated-v4-GGUF

53.7 tok/s · model median · 17 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RX 7900 XTX 24GB8-bit53.7 tok/smeasured-21.6 GB262,144llama.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.