Gemma 4 26B-A4B › NVIDIA RTX 3090 Ti

Gemma 4 26B-A4B on the NVIDIA RTX 3090 Ti

Gemma 4 26B-A4B runs at about 138 tokens/s on the NVIDIA RTX 3090 Ti (measured, Q4_K_M, CUDA, llama-bench).

Best measured: 138 tokens/s generation and 4,184 tokens/s prompt processing (Q4_K_M, CUDA).

For comparison, our size-scaling estimate for this combination is 128 tok/s.

Every run

QuantBackendGenerate tok/sPrompt tok/sTestBuild / by / notesSource
Q4_K_MCUDA 1384,184tg64 Comparison run in a stock container, same article.Algol Labs Gemma 4 benchmark

tg128 = generating 128 tokens; pp512 = reading a 512-token prompt (llama-bench). LocalScore averages several prompt and output lengths, so its numbers run lower than tg128. "decode, llama-server" = single-stream generation speed measured against a running llama-server (no speculative decoding).

Check prices

Amazon Newegg

As an Amazon Associate I earn from qualifying purchases.

No card yet?

Try it on a rented GPU (RunPod)

Affiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.

All results for the NVIDIA RTX 3090 Ti · Gemma 4 26B-A4B on other hardware

Embed this result

Gemma 4 26B-A4B · NVIDIA RTX 3090 Ti: 138 tok/s (Q4_K_M, measured)

HTML

<a href="https://rigbench.pages.dev/model/gemma-4-26b-a4b-it/on/nvidia-rtx-3090-ti/"><img src="https://rigbench.pages.dev/badge/gemma-4-26b-a4b-it--nvidia-rtx-3090-ti.svg" alt="Gemma 4 26B-A4B · NVIDIA RTX 3090 Ti: 138 tok/s (Q4_K_M, measured)"></a>

Markdown (GitHub README, forums)

[![Gemma 4 26B-A4B · NVIDIA RTX 3090 Ti: 138 tok/s (Q4_K_M, measured)](https://rigbench.pages.dev/badge/gemma-4-26b-a4b-it--nvidia-rtx-3090-ti.svg)](https://rigbench.pages.dev/model/gemma-4-26b-a4b-it/on/nvidia-rtx-3090-ti/)