Can I run it?
Can I run gemma 4 31B it on GeForce RTX 5060 Ti 16GB?
Tight fit
Tight fit fully on your GeForce RTX 5060 Ti 16GB at Q3_K_S, 4K context, about 14–19 tok/s. Weights 12.3 GB plus 1.41 GB of KV cache — 14.1 GB of 14.7 GB usable.
Best quantQ3_K_S
Working context4K
Max that fits4K
Speed14–19 tok/s
Weights12.3 GB
KV cache1.41 GB
Total14.1 GB
Usable14.7 GB
gemma 4 31B it details · GeForce RTX 5060 Ti 16GB page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/gemma-4-31B-it-GGUF:Q3_K_S -c 4096 -ngl 60
Ollama
ollama run gemma
LM Studio
lms get unsloth/gemma-4-31B-it-GGUF # Then load quant Q3_K_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%.
- Q3_K_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 4K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.6 35B A3B on GeForce RTX 5060 Ti 16GB? — Tight fit, UD-IQ3_S, 182–249 tok/s
- Can I run Qwen3.8 35B A3B Distill on GeForce RTX 5060 Ti 16GB? — Tight fit, Q2_K, 184–251 tok/s
- Can I run Qwen3.5 35B A3B on GeForce RTX 5060 Ti 16GB? — Tight fit, UD-IQ3_S, 183–250 tok/s
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.