Can I Run Gemma 3 12B Instruct on NVIDIA GeForce RTX 5090?
Written by Jakub Rusinowski · Last updated September 29, 2026
Yes. Gemma 3 12B Instruct needs 11.1 GB at 8K context (7.2 GB weights + 3.9 GB KV cache/overhead) at Q4_K_M and the NVIDIA GeForce RTX 5090 has 32 GB, leaving about 20.9 GB of headroom, at roughly 125 tok/s (estimated) with room for up to 32K of context.
See what else this hardware can run →
The numbers
| Model | Gemma 3 12B Instruct |
| Parameters | 12B |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 11.1 GB |
| NVIDIA GeForce RTX 5090 VRAM | 32 GB |
| Verdict | Runs |
| Max context | 32K |
| Estimated speed | ~125 tok/s |
Gemma 3 12B Instruct on the NVIDIA GeForce RTX 5090: VRAM by quantization
| Quant | VRAM needed | Fits 32 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 27.9 GB | ✓ Yes | 16K | — |
| Q8_0 | 16.6 GB | ✓ Yes | 32K | Build for this |
| Q6_K | 13.7 GB | ✓ Yes | 32K | — |
| Q5_K_M | 12.4 GB | ✓ Yes | 32K | Build for this |
| Q4_K_M | 11.1 GB | ✓ Yes | 32K | Build for this |
| Q3_K_M | 9 GB | ✓ Yes | 64K | — |
| Q2_K | 7.8 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 32 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA GeForce RTX 5090: 8K 11.1 GB · 32K 20.4 GB · 128K 57.4 GB ✗. Past 128K it no longer fits 32 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? Gemma 3 12B Instruct on 16 GB of system RAM, CPU only: runs, but it is tight.
Running Gemma 3 12B Instruct on this card:
At 2 hrs/day, buying (~$1,999) beats renting at $0.34/hr after about 8.2 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Other Gemma 3 sizes on the NVIDIA GeForce RTX 5090
- Gemma 3 27B Instruct — runs (25.4 GB)
- Gemma 3 4B Instruct — runs (4.4 GB)
- Gemma 3 1B Instruct — runs (2 GB)
Gemma 3 12B Instruct on nearby hardware
- AMD Radeon RX 7900 XTX (24 GB) — runs
- Apple M3 Pro (36 GB) — runs
All Gemma 3 sizes on the NVIDIA GeForce RTX 5090 | Gemma 3 12B Instruct model page | NVIDIA GeForce RTX 5090 GPU page | VRAM calculator | Check your hardware