Can Gemma 4 31B IT run on the RTX 4060 Ti 16GB?
Yes. At 8K context the best fit is Q2_K, using about 14.7 GB of the 15.2 GB usable on the RTX 4060 Ti 16GB. Estimated speed ceiling: ~23 tokens/sec.
Better quality with offload: 4-bit (Q4_K_M)
Runs with offload 4-bit (Q4_K_M) at 8K context: 40 of 60 layers on the RTX 4060 Ti 16GB (about 14.4 GB) and the other 20 in system RAM (about 6.8 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 2.9–5.0 tokens/sec (slow but usable), versus a bandwidth ceiling of ~15 tok/s if it fit fully in VRAM.
llama-server -hf bartowski/google_gemma-4-31B-it-GGUF:Q4_K_M -c 8192 -ngl 40
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, lower -ngl by 2-3; if VRAM is left over, raise 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. Sending images also loads the vision projector (mmproj) file: Q2_K at 8K context then needs about 15.8 GB (no longer fits, so drop one quant or shorten the context). Calculator with image input on.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 14.1 GB Tight | 14.7 GB Tight | 18.4 GB No | 33.4 GB No | 23 |
| 3-bit (Q3_K_M) • | 17.1 GB No | 17.8 GB No | 21.5 GB No | 36.5 GB No | — |
| 4-bit (Q4_K_M) • | 20.6 GB No | 21.2 GB No | 24.9 GB No | 39.9 GB No | — |
| 5-bit (Q5_K_M) • | 23.4 GB No | 24.0 GB No | 27.7 GB No | 42.7 GB No | — |
| 6-bit (Q6_K) • | 27.2 GB No | 27.8 GB No | 31.6 GB No | 46.6 GB No | — |
| 8-bit (Q8_0) • | 32.7 GB No | 33.3 GB No | 37.1 GB No | 52.1 GB No | — |
| 16-bit (F16/BF16) • | 59.5 GB No | 60.1 GB No | 63.9 GB No | 78.9 GB No | — |
• real GGUF file size from bartowski/google_gemma-4-31B-it-GGUF. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Gemma 4 31B IT: RTX 5090 (32 GB, launch MSRP $1,999) at Q5_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 4060 Ti 16GB: gpt-oss 20B (21B, MoE) at Q8_0, about 12.3 GB at 8K context.
"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 31B 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-4-31B-it), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.