Gemma on NVIDIA Ada
Can I run Gemma 3 12B on an RTX 4060 Ti 16GB?
Yes. Gemma 3 12B at Q4_K_M uses 8.6 GB of the 14.2 GB available on a RTX 4060 Ti 16GB, and runs at about 22.8 tokens per second. You can push the context to 98K.
Runs comfortably
8.6 GB of 14.2 GB · 60%014 GB
Weights
7.0 GB
KV cache
0.8 GB
Runtime overhead
0.8 GB
Gemma 3 12B at Q4_K_M leaves 5.6 GB spare on a RTX 4060 Ti 16GB. There is room to raise the context length or move up a quantisation level.
Generation22.8tok/s
Prompt processing757tok/s
Max context98Ktokens
KV per 1K tokens0GB
Every quantisation of Gemma 3 12B on a RTX 4060 Ti 16GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 22.7 GB | 24.4 GB | Won't fit | — | 2.84 |
| INT8 / W8A8 | 8.50 | 11.8 GB | 13.5 GB | Fits, but tight | 20K | 13.9 |
| Q8_0 (GGUF) | 8.50 | 11.8 GB | 13.5 GB | Fits, but tight | 20K | 13.9 |
| FP8 (E4M3) | 8.00 | 11.4 GB | 13.0 GB | Fits, but tight | 28K | 14.4 |
| Q6_K | 6.56 | 9.3 GB | 10.9 GB | Runs comfortably | 61K | 17.4 |
| Q5_K_M | 5.67 | 8.1 GB | 9.7 GB | Runs comfortably | 81K | 19.9 |
| Q5_K_S | 5.52 | 7.8 GB | 9.5 GB | Runs comfortably | 84K | 20.4 |
| AWQ 4-bit | 4.25 | 7.4 GB | 9.0 GB | Runs comfortably | 91K | 21.5 |
| GPTQ 4-bit | 4.25 | 7.4 GB | 9.0 GB | Runs comfortably | 91K | 21.5 |
| MXFP4 | 4.25 | 7.4 GB | 9.0 GB | Runs comfortably | 91K | 21.5 |
| Q4_K_M | 4.85 | 7.0 GB | 8.6 GB | Runs comfortably | 98K | 22.8 |
| Q4_K_S | 4.58 | 6.6 GB | 8.2 GB | Runs comfortably | 104K | 23.9 |
| Q4_0 | 4.55 | 6.6 GB | 8.2 GB | Runs comfortably | 105K | 24.0 |
| IQ4_XS | 4.25 | 6.2 GB | 7.8 GB | Runs comfortably | 111K | 25.4 |
| Q3_K_M | 3.91 | 5.7 GB | 7.4 GB | Runs comfortably | 118K | 27.2 |
| IQ3_M | 3.70 | 5.5 GB | 7.1 GB | Runs comfortably | 122K | 28.4 |
| IQ3_XXS | 3.06 | 4.6 GB | 6.3 GB | Runs comfortably | 128K | 32.9 |
| Q2_K | 2.63 | 4.1 GB | 5.7 GB | Runs comfortably | 128K | 36.9 |
| IQ2_XXS | 2.06 | 3.3 GB | 5.0 GB | Runs comfortably | 128K | 43.8 |
| IQ1_M | 1.75 | 2.9 GB | 4.6 GB | Runs comfortably | 128K | 48.8 |