Can I run it?
Can I run gemma 4 31B it on GeForce RTX 4060?
Partial offload
Partial offload on your GeForce RTX 4060: Q4_K_M at 4K context, 18 of 60 layers on the GPU and 11.8 GB in system RAM. Expect about 3.3–4.5 tok/s.
Best quantQ4_K_M
Working context4K
Max that fits4K
Speed3.3–4.5 tok/s
Weights17.1 GB
KV cache1.41 GB
Total18.9 GB
Usable7.13 GB
gemma 4 31B it details · GeForce RTX 4060 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/gemma-4-31B-it-GGUF:Q4_K_M -c 4096 -ngl 18
Ollama
ollama run gemma
LM Studio
lms get unsloth/gemma-4-31B-it-GGUF # Then load quant Q4_K_M
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%.
- Q4_K_M 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.
- About 18 of 60 layers stay on the GPU. 11.8 GB is read from system RAM.
Models that fit this machine more comfortably
- Can I run Qwen3.8 27B on GeForce RTX 4060? — Tight fit, UD-IQ1_M, 21–29 tok/s
- Can I run gemma 3 27b it on GeForce RTX 4060? — Tight fit, UD-IQ1_S, 21–29 tok/s
- Can I run medgemma 27b text it on GeForce RTX 4060? — Tight fit, UD-IQ1_S, 20–27 tok/s
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.