§01·compatibility · /check
Gemma4 31B on RTX 3090
Yes — Gemma4 31B runs on the RTX 3090 (24 GB). Fastest community-measured result: 1155.8 prefill tokens/s, with 24 GB peak VRAM.
✓ runsmultimodalactive30 series24GB VRAM
step-by-step recipe for this pair
Gemma 4 31B on RTX 3090: dense 31B local chat via Q4_K_M GGUF in Ollama / llama.cpp
llmintermediate24GB+
§02·benchmarks
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| llm | Q4_K | 1155.8prefill tokens/s | 24GB | ✓ | hardware-corner.net· web | 2026-05-15 | |
| llm | Q4_K | 34.7tokens/s | 24GB | ✓ | hardware-corner.net· web | 2026-05-15 |
§03·more Gemma4 31B recipes
§04·common questions
Can you run Gemma4 31B on RTX 3090?
Yes — Gemma4 31B runs on the RTX 3090 (24 GB). Fastest community-measured result: 1155.8 prefill tokens/s, with 24 GB peak VRAM.
How much VRAM does Gemma4 31B need on RTX 3090?
Measured peak VRAM is 24 GB.
Which quantizations have been tested for Gemma4 31B on RTX 3090?
Q4_K — measured in community benchmarks.
How fast is Gemma4 31B on RTX 3090?
Up to 1155.8 prefill tokens/s (llm), the fastest community-measured result.
Are there step-by-step instructions for Gemma4 31B on RTX 3090?
Yes — a step-by-step recipe documents Gemma4 31B on the RTX 3090, linked at the top of this page.