✅Runs wellfp16 · 4K ctx · batch 1

Run Gemma 2 9B on RTX 5090

At fp16 precision, Gemma 2 9B (9.0 B parameters) needs roughly 20.9 GB of VRAM. RTX 5090 has 32 GB, leaving 11.1 GB of headroom — plenty of room for longer contexts and larger batch sizes. Expected throughput ≈ 99 tokens/sec on a single card.

65%
VRAM
Runs well
Estimated VRAM (fp16)
20.9 GB
of 32 GB on RTX 5090· 11.1 GB free
Tok/sec
99
TFTT
675ms
Power
222W
Rent on GPUniq marketplace
RTX 5090
Live prices from verified providers · billed hourly, no commitment.
Rent now

Memory breakdown (fp16)

Model Weights
18.00 GB
KV Cache
0.37 GB
Activations
1.48 GB
Framework Overhead
1.04 GB

Quantization comparison

Lower precision = less VRAM with a small quality trade-off. Quality order: FP16 > INT8 > INT4.

PrecisionVRAMUtilisationFits on RTX 5090?
FP16 (full precision)20.9 GB65%✅Runs well
INT8 (8-bit)11.1 GB35%✅Runs easily
INT4 / Q4 (4-bit)6.2 GB20%✅Runs easily

Frequently asked

Can RTX 5090 run Gemma 2 9B?
Yes. Gemma 2 9B needs ≈ 20.9 GB VRAM at fp16 and RTX 5090 provides 32 GB. Expected throughput is 99 tokens/sec per GPU.
How much VRAM does Gemma 2 9B use?
About 20.9 GB at fp16, 6.2 GB at INT4 (for a 4K context, batch size 1). Longer contexts add to KV cache size; larger batches increase activations.
What's the fastest way to run Gemma 2 9B on RTX 5090?
Use a production inference engine like vLLM, SGLang, or TensorRT-LLM with paged attention — they cut KV cache 2–3× vs the naive estimate and batch multiple requests efficiently. For RTX 5090, enable Flash Attention 2.
Where can I rent a RTX 5090?
GPUniq aggregates live RTX 5090 offers from verified providers. You can deploy an instance in about a minute and pay hourly with no commitment.

Other GPUs for Gemma 2 9B

Other models on RTX 5090

Try it live

Chat with Gemma 2 9B — no setup

Send a prompt and see how Gemma 2 9B responds directly in our chat. No installation, no GPU required to test.

Open in chat
Want to tweak sequence length, batch size, or fine-tuning? Open the full calculator →