Can RTX 5070 Ti run Gemma 4 26B-A4B?
Last updated:
Yes. Measured 59.4 tok/s generation (llama.cpp b11669 (CUDA), partial CPU offload, UD-IQ4_XS (13.6 GB); source).
Every measured result for Gemma 4 26B-A4B on RTX 5070 Ti
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| RTX 5070 Ti + Ryzen 9 5950X: gpt-oss 20B at 213.2 tok/s, Qwen3.5 9B at 126.6 (llama.cpp CUDA) | UD-IQ4_XS (13.6 GB) | llama.cpp b11669 (CUDA), partial CPU offload | 59.4 | source |
Memory: RTX 5070 Ti has 16 GB. Gemma 4 26B-A4B weights are about 15.4 GB at Q4_K_M (25.23B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for Gemma 4 26B-A4B: best home rig for Gemma 4 26B-A4B.
Gemma 4 26B-A4B on other hardware: DGX Spark (GB10) · Intel Arc Pro B70 · RTX 4090 · RTX 5090 · RTX Spark N1X · Strix Halo (Radeon 8060S)
Other models measured on RTX 5070 Ti: Gemma 4 12B · Qwen3.5 9B · Qwen3.8 27B · gpt-oss 20B
Not enough VRAM? Rent before you buy. Run Gemma 4 26B-A4B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.