community pool / model answer

Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF

chat · llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF

26.1 tok/s · model median · 11 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB4-bit26.1 tok/smeasured214- GB131,072llama.cpp, vllm

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.