community pool / model answer

Qwen3.5-0.8B-MTP-GGUF

chat · unsloth/Qwen3.5-0.8B-MTP-GGUF

434.1 tok/s · model median · 2 runs in the model record.

Answer

434.1tok/s

reportedRTX 3090 24GB6-bit · 2 runs · decodebest cell in the pool

  1. RTX 3090 24GB434.1 tok/sreported2 runs · peak 1.5 GB · fits 24 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB6-bit434.1 tok/sreported451.5 GB24,576llama.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.