Can I run it?

Can I run Qwen3.6 35B A3B on GeForce RTX 4070 Ti Super?

Tight fit

Tight fit fully on your GeForce RTX 4070 Ti Super at UD-IQ3_S, 8K context, about 273–373 tok/s. Weights 12.7 GB plus 0.19 GB of KV cache — 13.4 GB of 14.7 GB usable. Up to 32K context still fits.

Best quantUD-IQ3_S

Working context8K

Max that fits32K

Speed273–373 tok/s

Weights12.7 GB

KV cache0.19 GB

Total13.4 GB

Usable14.7 GB

Qwen3.6 35B A3B details · GeForce RTX 4070 Ti Super page · How this estimate is made

Run commands

llama.cpp

llama-server -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-IQ3_S -c 8192 -ngl 40

Ollama

ollama run qwen3.6

LM Studio

lms get unsloth/Qwen3.6-35B-A3B-GGUF
# Then load quant UD-IQ3_S

Assumptions

Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
UD-IQ3_S size is the real GGUF file size from Hugging Face.
0.5 GB is reserved because this GPU also drives a display, then 5% of the rest is left free.
Speed is quoted at 8K context, not at the maximum context that still fits.

Larger models that also fit

Can I run Qwen3.8 35B A3B Distill on GeForce RTX 4070 Ti Super? — Tight fit, Q2_K, 276–377 tok/s
Can I run Qwen3.5 35B A3B on GeForce RTX 4070 Ti Super? — Tight fit, UD-IQ3_S, 275–375 tok/s
Can I run Cyber Tiel Coder 35B A3B GGUF MTP on GeForce RTX 4070 Ti Super? — Tight fit, Q2_K, 276–376 tok/s

Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.