community pool / model answer

Qwen3.5-4B-MTP-GGUF

chat · unsloth/Qwen3.5-4B-MTP-GGUF

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

Answer

191.2tok/s

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

  1. RTX 3090 24GB191.2 tok/sreported2 runs · peak 5.4 GB · fits 24 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB6-bit191.2 tok/sreported1295.4 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.