Can I Run Gemma 2 Family on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?

Superseded model. Gemma 2 Family has been superseded by Gemma 4. This page is kept for reference; the newer family is a better starting point. View Gemma 4 →

Written by Jakub Rusinowski · Last updated June 27, 2024

Yes — comfortably

Yes, comfortably — Gemma 2 9B IT at Q8_0 needs about 13.2 GB of the 24 GB usable on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM), leaving ~10.8 GB spare and running at ~55.9 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~55.9 tok/s

RTX 3090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models	24 GB
Memory bandwidth	936 GB/s
Form factor	Desktop
Operating system	Windows or Linux
Memory upgradeable	Yes

Gemma 2 Family on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization

Quant	Memory needed	Fits 24 GB?	Max context	Est. speed	Download
F16	21.6 GB	✓ Yes	8K	~33.5 tok/s	18 GB
Q8_0	13.2 GB	✓ Yes	8K	~55.9 tok/s	9.6 GB
Q6_K	11 GB	✓ Yes	8K	~67.7 tok/s	7.4 GB
Q5_K_M	10 GB	✓ Yes	8K	~75 tok/s	6.4 GB
Q4_K_M	9.1 GB	✓ Yes	8K	~83.4 tok/s	5.4 GB
Q3_K_M	7.5 GB	✓ Yes	8K	~102.9 tok/s	3.8 GB
Q2_K	6.6 GB	✓ Yes	8K	~118.1 tok/s	3 GB

RTX 3090 desktop limitations

The cheapest route to 24 GB of VRAM, and the standard used-market recommendation for local LLMs.
Older architecture: no FP8 acceleration, and higher idle power than a current card.

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
24 GB of VRAM on the NVIDIA GeForce RTX 3090 at 936 GB/s.
64 GB of system RAM available for CPU offload when a model exceeds VRAM.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is computed from this model's published attention configuration.

FAQ