community pool / model answer

Qwen-AgentWorld-35B-A3B-B70-Turbo-GGUF

chat · Frosty40/Qwen-AgentWorld-35B-A3B-B70-Turbo-GGUF

90.3 tok/s · model median · 4 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Arc Pro B70 32GB5-bit66 tok/smeasured1,342- GB65,664llama.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.