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

Can Granite 4.1 3B Llmon Preview run on the RTX 3060 Ti?

Yes. At 8K context the best fit is Q8_0, using about 4.8 GB of the 7.6 GB usable on the RTX 3060 Ti. Estimated speed ceiling: ~115 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •2.3 GB Fits2.6 GB Fits4.4 GB Fits11.9 GB No308
3-bit (Q3_K_M) •2.6 GB Fits2.9 GB Fits4.8 GB Fits12.3 GB No244
4-bit (Q4_K_M) •3.0 GB Fits3.3 GB Fits5.2 GB Fits12.7 GB No200
5-bit (Q5_K_M) •3.3 GB Fits3.7 GB Fits5.5 GB Fits13.0 GB No171
6-bit (Q6_K) •3.7 GB Fits4.0 GB Fits5.9 GB Fits13.4 GB No149
8-bit (Q8_0) •4.5 GB Fits4.8 GB Fits6.7 GB Fits14.2 GB No115
16-bit (F16/BF16)7.7 GB No8.0 GB No9.9 GB No17.4 GB No—

• real GGUF file size from liodon-ai/granite-4.1-3b-llmon-preview-GGUF. Speed is a bandwidth ceiling (448 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

Granite 4.1 3B Llmon Preview on every GPU and Mac · Every model that runs on the RTX 3060 Ti · Other models that fit 8 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 (ibm-granite/granite-4.1-3b-llmon-preview), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.