RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can Gemma 4 26B A4B IT run on the RTX 4060 Ti 16GB?

Yes. At 8K context the best fit is Q3_K_M, using about 13.5 GB of the 15.2 GB usable on the RTX 4060 Ti 16GB. Estimated speed ceiling: ~143 tokens/sec.

Better quality with offload: 4-bit (Q4_K_M)

Runs with offload 4-bit (Q4_K_M) at 8K context: all attention layers plus the experts of 24 of 30 MoE layers on the RTX 4060 Ti 16GB (about 13.6 GB), and the experts of the other 6 layers in system RAM (about 2.8 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 46–58 tokens/sec (usable for chat), versus a bandwidth ceiling of ~109 tok/s if it fit fully in VRAM.

llama-server -hf bartowski/google_gemma-4-26B-A4B-it-GGUF:Q4_K_M -c 8192 -ngl 999 --n-cpu-moe 6 --no-mmproj

Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, raise --n-cpu-moe by 1-2; if VRAM is left over, lower it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.

+ 1.1 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q3_K_M at 8K context then needs about 14.6 GB (tight). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.5 GB Fits11.6 GB Fits12.5 GB Fits16.3 GB No170
3-bit (Q3_K_M) •13.4 GB Fits13.5 GB Fits14.5 GB Tight18.2 GB No143
4-bit (Q4_K_M) •17.1 GB No17.3 GB No18.2 GB No22.0 GB No—
5-bit (Q5_K_M) •19.2 GB No19.4 GB No20.3 GB No24.1 GB No—
6-bit (Q6_K) •22.5 GB No22.7 GB No23.6 GB No27.4 GB No—
8-bit (Q8_0) •26.3 GB No26.4 GB No27.4 GB No31.1 GB No—
16-bit (F16/BF16) •48.3 GB No48.4 GB No49.4 GB No53.1 GB No—

• real GGUF file size from bartowski/google_gemma-4-26B-A4B-it-GGUF. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Gemma 4 26B A4B IT on every GPU and Mac · Every model that runs on the RTX 4060 Ti 16GB · Other models that fit 16 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (google/gemma-4-26B-A4B-it), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.