Can an RTX 5070 Ti run Gemma 4 31B Instruct?
Barely
It only loads at IQ3_XXS, which compresses the weights far enough to visibly degrade the model, so we would not call that running it.
In practice
It loads, and we would not call that running it. The only quantization that fits the GeForce RTX 5070 Ti is IQ3_XXS, which compresses the weights far enough that Gemma 4 31B Instruct loses a visible amount of its ability, so we do not recommend it. At Q4_K_M it needs 21.31 GB against the 15.2 GB available.
Running it properly means a split with system RAM: at Q4_K_M about 42 of 60 layers fit on the card, and the estimate falls to 4.3 tokens per second. A smaller model at a proper quantization is a better answer than a larger one squeezed in, and the next section lists the ones that fit.
The numbers
Gemma 4 31B Instruct has 31.27 billion parameters across 60 layers. The GeForce RTX 5070 Ti has 16 GB of VRAM at 896 GB/s, of which about 15.2 GB is left for a model once the operating system has taken its share.
| Quantization | Total needed | Fits | Speed |
|---|---|---|---|
| Q8_0 | 34.67 GB | partial | 1.5 t/s |
| Q6_K | 27.61 GB | partial | 2.2 t/s |
| Q5_K_M | 24.44 GB | partial | 2.9 t/s |
| Q4_K_M | 21.31 GB | partial | 4.3 t/s |
| IQ4_XS | 19.2 GB | partial | 6.3 t/s |
| Q3_K_M | 17.96 GB | partial | 8.4 t/s |
| IQ3_XXS degraded | 14.87 GB | yes | 45.7 t/s |
| Q2_K degraded | 15.93 GB | partial | 20.8 t/s |
| IQ2_XXS degraded | 11.23 GB | yes | 61.2 t/s |
2 of the 9 levels fit entirely. Levels marked degraded are listed for completeness, not as advice. Rows marked partial or experts in RAM run with part of the model in system RAM, at the speed shown.
What to run instead
A smaller model from the same family is the straightforward answer. These fit on an RTX 5070 Ti at a quantization worth using:
- Gemma 3 27B Instruct, 27.43B at IQ4_XS, 15.11 GB, about 45.0 tokens/s
- Gemma 4 26B A4B Instruct, 25.81B at IQ4_XS, 13.96 GB, about 143 tokens/s
- Gemma 3 12B Instruct, 12.19B at Q8_0, 13.27 GB, about 51.2 tokens/s
Shortening the context will not rescue this one: at 4k it still wants 20.06 GB against 21.31 GB at 8k, because the weights, not the cache, are what fill the card.
Models of this size are what a second GPU or a large-memory machine is for. The multi-GPU guide shows what 2 cards add, and the Mac and PC comparison shows where unified memory holds a model that no single card can.
Or the hardware that does run it
The cheapest device we track that runs Gemma 4 31B Instruct at a quantization worth using is the GeForce RTX 3090, around $700 used , running it at Q4_K_M at about 33.0 tokens per second. Check the current price (affiliate link, indicative price reviewed 2026-09-01). Compare every option.
What else an RTX 5070 Ti runs well
For comparison, these are the other popular models that fit this device at a sound quantization, best pairings first.
| Model | Quantization | Memory | Speed |
|---|---|---|---|
| Qwen3.5 27B | IQ4_XS | 14.2 GB | 47.9 t/s |
| Gemma 4 12B Instruct | Q8_0 | 13.55 GB | 50.1 t/s |
| GPT OSS 20B | MXFP4 | 11.55 GB | 160 t/s |
| Qwen3 14B | Q6_K | 12.38 GB | 55.2 t/s |
The same model on nearby hardware
Memory decides whether Gemma 4 31B Instruct loads and bandwidth decides how quickly it answers. Here is what a step down, a card with the same memory and a step up do with it.
| Device | Memory | Bandwidth | Result |
|---|---|---|---|
| GeForce RTX 4070 | 12 GB | 504 GB/s | partial, 2.7 t/s |
| GeForce RTX 5080 | 16 GB | 960 GB/s | does not fit |
| GeForce RTX 4090 | 24 GB | 1008 GB/s | Q4_K_M, 35.5 t/s |
Questions people ask
How much VRAM does Gemma 4 31B Instruct need on RTX 5070 Ti?
At Q4_K_M with an 8k context window it needs 21.31 GB in total: 17.58 GB of weights, 3.28 GB of KV cache and 0.45 GB of runtime overhead. The GeForce RTX 5070 Ti makes about 15.2 GB available once the operating system has taken its share.
What should I run instead of Gemma 4 31B Instruct on RTX 5070 Ti?
Gemma 3 27B Instruct fits at IQ4_XS and runs at about 45.0 tokens per second. Smaller models from the same family are the usual answer.
Keep going
Everything the GeForce RTX 5070 Ti runs, the full breakdown for Gemma 4 31B Instruct, how the numbers are made in the methodology, or a different pairing in the calculator.