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
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | CUDA | 138 | 4,184 | tg64 | 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).
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
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)
[](https://rigbench.pages.dev/model/gemma-4-26b-a4b-it/on/nvidia-rtx-3090-ti/)