Qwen3.6 35B (3B active)
on 2× NVIDIA RTX 5070 Ti · Ollama/llama.cpp · 16,384 ctx
Use cases
coding
Summary
User reports Qwen 3.6 35B-A3B at around 82 tok/s with a 16k context on an RTX 5070 Ti paired with an RTX 3070.
Setup is Ollama/llama.cpp splitting the model across the two mismatched cards, with the 3070 on an x1 PCIe riser.
About 23% of layers spill into system RAM and the split ratio between cards is not yet tuned; the 3070 has about 4GB sitting unused.