Can the RTX 5090 D run Gemma 4 12B?
Yes. Gemma 4 12B fits the RTX 5090 D's 32 GB at Q4_K_M (about 8.8 GB needed), running at an estimated 147 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Gemma 4 12B (12B) on 32 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 7 GB | 8.8 GB | Fits easily | ~147 tok/s |
| Q5_K_M | 9 GB | 10.8 GB | Fits easily | ~114 tok/s |
| Q8_0 | 13 GB | 14.8 GB | Fits easily | ~79 tok/s |
| FP16 | 24 GB | 25.8 GB | Fits | ~43 tok/s |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 5090 D's 1790 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf google/gemma-4-12B-it-qat-q4_0-gguf -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Gemma 4 12B details →
Compare
Same model, other hardware - and other models on this card
Gemma 4 12B on other hardware
- RTX 5090~147 tok/s
- RTX 6000D~129 tok/s
- RTX 4090~89 tok/s
- Radeon RX 7900 XTX~79 tok/s
- RTX 5080~79 tok/s
- RTX 3090~78 tok/s
- RTX 3080 Ti~75 tok/s
- RTX 5080 Mobile~73 tok/s
Also runs on the RTX 5090 D
- Qwen3.6 35B A3B~391 tok/s
- Qwen3.5 35B A3B~391 tok/s
- dolphin-2.9.1-yi-1.5-34b~51 tok/s
- Gemma 4 31B~54 tok/s
- Qwen3 32B~54 tok/s
- GLM-4.7-Flash~395 tok/s
- Qwen3-30B-A3B-Instruct-2507~387 tok/s
- Qwen3.6 27B~64 tok/s
Frequently asked
Quick answers
Can the GeForce RTX 5090 D run Gemma 4 12B?
Yes. Gemma 4 12B fits the RTX 5090 D's 32 GB at Q4_K_M (about 8.8 GB needed), running at an estimated 147 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Gemma 4 12B need?
About 7 GB of weights at Q4_K_M, 13 GB at Q8_0 and 24 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Gemma 4 12B on the RTX 5090 D?
Roughly 147 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 5090 D's 1790 GB/s memory bandwidth.