Can an RTX 3050 8GB run Gemma 4 31B Instruct?
Partly
Not entirely. About 20 of its 60 layers fit on the card and the rest run on the CPU, which brings generation down to roughly 2.4 tokens per second.
The numbers
Gemma 4 31B Instruct has 31.27 billion parameters across 60 layers. The GeForce RTX 3050 8GB has 8 GB of VRAM at 224 GB/s, of which about 7.2 GB is left for a model once the operating system has taken its share.
| Quantisation | Total needed | Fits | Speed |
|---|---|---|---|
| Q8_0 | 32.81 GB | no | — |
| Q6_K | 25.75 GB | no | — |
| Q5_K_M | 22.58 GB | no | — |
| Q4_K_M | 19.45 GB | no | — |
| IQ4_XS | 17.34 GB | no | — |
| Q3_K_M | 16.1 GB | no | — |
| IQ3_XXS degraded | 13.01 GB | no | — |
| Q2_K degraded | 14.06 GB | no | — |
| IQ2_XXS degraded | 9.37 GB | no | — |
Nothing on this ladder fits, including the two-bit levels we do not recommend.
What to do instead
The straightforward answer is a smaller model from the same family. These do fit on a GeForce RTX 3050 8GB, at a quantisation worth using:
- Gemma 3 12B Instruct — 12.19B at Q3_K_M, 7.2 GB, about 28.9 tokens/s
- Gemma 4 12B Instruct — 11.96B at IQ4_XS, 7.13 GB, about 29.2 tokens/s
- Gemma 2 9B Instruct — 9.24B at IQ4_XS, 6.7 GB, about 31.2 tokens/s
You can also run it as is. Ollama and llama.cpp will put 20 of the 60 layers on the card and the rest on the CPU without being asked. It works, at roughly 2.4 tokens per second, which is fine for a batch job and tiring for a conversation.
Shortening the context window will not rescue this one: at 4k it still wants 19.29 GB against 19.45 GB at 8k, because the weights rather than the cache are what fill the card. The gap here is too large for settings to close.
Or the hardware that does run it
The cheapest device we track that runs Gemma 4 31B Instruct at a quantisation worth using is the Radeon RX 7900 XT, around $650 , running it at IQ4_XS at about 35.1 tokens per second. Check the current price (affiliate link; indicative price reviewed 2026-09-01). Compare every option.
See how fast it feels
GeForce RTX 3050 8GB running Gemma 4 31B Instruct, 20 of 60 layers on the GPU
YouWhy does my model use more memory when the conversation gets longer?
Because of the KV cache. Every token you send leaves behind a key and a value vector in each layer of the model, and those stay in memory for as long as the conversation lasts.
The weights are a fixed cost: load a 4-bit 8B model and that is about 4.8 GB, whether you write one word or ten thousand. The cache is the part that grows, and it grows in a straight line with the number of tokens in the window.
How steeply depends on the model's attention design. With grouped-query attention, several query heads share one key-value pair, which cuts the cache by that ratio. Without it, every head keeps its own, and a long context can cost more memory than the weights themselves.
If you are short on memory, the first thing to try is lowering the context window in your runtime, not the quantisation.
Reading your question
Simulated from our estimate at a 512-token question, not a recording. Assumes nothing else is competing for the GPU. The same answer on RTX 4090 at Q5_K_M would take about 4.8 s.
Keep going
Everything the GeForce RTX 3050 8GB runs, the full breakdown for Gemma 4 31B Instruct, or check a different pairing in the calculator.