Can RTX 5090 run Gemma 4 31B?
Yes. Measured 70.0 tok/s generation (llama.cpp, llama-bench tg128 (quant per result); source).
Every measured result for Gemma 4 31B on RTX 5090
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| RTX 5090: 2026 models (llamabench community) | llama-bench tg128 (quant per result) | llama.cpp | 70.0 | source |
Memory: RTX 5090 has 32 GB. Gemma 4 31B weights are about 18.8 GB at Q4_K_M (30.7B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for Gemma 4 31B: best home rig for Gemma 4 31B.
Gemma 4 31B on other hardware: RTX 4090
Other models measured on RTX 5090: Gemma 4 12B · Gemma 4 26B-A4B · Qwen3.5 9B · Qwen3.6 27B · Qwen3.6 35B-A3B · gpt-oss 20B
Not enough VRAM? Rent before you buy. Run Gemma 4 31B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on RunPod
Referral link: RigBase may earn RunPod credit if you sign up. It never affects our data.
Referral link: RigBase may earn RunPod credit if you sign up. It never affects our data.
SPONSOR
Your brand here. One sponsor slot on this page, shown to people choosing AI hardware. Sponsor RigBase →
Your brand here. One sponsor slot on this page, shown to people choosing AI hardware. Sponsor RigBase →