Can I run it?
Can I run gemma 4 12b it on GeForce RTX 3080 10GB?
Tight fit
Tight fit fully on your GeForce RTX 3080 10GB at Q5_K_M, 4K context, about 42–57 tok/s. Weights 7.84 GB plus 0.56 GB of KV cache — 8.78 GB of 9.03 GB usable.
Best quantQ5_K_M
Working context4K
Max that fits4K
Speed42–57 tok/s
Weights7.84 GB
KV cache0.56 GB
Total8.78 GB
Usable9.03 GB
gemma 4 12b it details · GeForce RTX 3080 10GB page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/gemma-4-12b-it-GGUF:Q5_K_M -c 4096 -ngl 48
Ollama
ollama run gemma
LM Studio
lms get unsloth/gemma-4-12b-it-GGUF # Then load quant Q5_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%.
- Q5_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.
Larger models that also fit
- Can I run Qwen3.8 27B on GeForce RTX 3080 10GB? — Tight fit, UD-IQ2_S, 47–64 tok/s
- Can I run Qwen3.6 14B A3B FableVibes on GeForce RTX 3080 10GB? — Tight fit, Q4_K_M, 208–283 tok/s
- Can I run Qwen2.5 14B Instruct on GeForce RTX 3080 10GB? — Tight fit, IQ4_XS, 47–64 tok/s
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.