Yes, just — 1.4 GB spare
Gemma 3 12B at Q4_K_M fits your GeForce RTX 2080 Ti entirely on the GPU at 8K context, at an estimated 54 tokens per second. Past 30K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Strong multilingual chat with images, sized for 12–16 GB cards. Gemma 4 12B is the same size and better.
Hardware requirements What hardware do I need to run Gemma 3 12B? →At Q4_K_M with an 8K context: a 12 GB GPU (RTX 3060 12 GB) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 22.7 GB | 24.1 GB | — | ~2.4 | Reference | 14.4 GB over |
| Q8_0 | 12.1 GB | 13.5 GB | — | ~7.9 | −0.1% ppl | 3.8 GB over |
| Q6_K | 9.3 GB | 10.7 GB | — | ~20 | −0.4% ppl | 1.0 GB over |
| Q5_K_M | 8.1 GB | 9.5 GB | 11K | 46 | −0.8% ppl | Fits |
| Q4_K_M | 6.9 GB | 8.3 GB | 30K | 54 | −1.9% ppl | Recommended |
| Q3_K_M | 5.6 GB | 7.0 GB | 51K | 67 | −5.4% ppl | Long context |
| Q2_K | 4.8 GB | 6.2 GB | 64K | 78 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (1024 tokens, 1 global in 6), which is why its cache barely grows with context.
How to run it
$ llama-server \
-hf google/gemma-3-12b-it:Q4_K_M \
-c 8192 -ngl 99
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a GeForce RTX 2080 Ti
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Gemma 3 27B 27.4B · same family |
Q4_K_M · 17.0 GB | ~4.5 | CPU offload |
| Gemma 3 4B 4.3B · same family |
Q4_K_M · 3.3 GB | 154 | Runs great |
| Gemma 3 1B 1.0B · same family |
Q4_K_M · 1.2 GB | 663 | Runs great |
| Mistral NeMo 12B 12.2B · similar size |
Q4_K_M · 8.7 GB | 54 | Tight fit |
| Gemma 4 12B 12B · similar size |
Q4_K_M · 8.2 GB | 55 | Runs great |
| Ministral 3 14B 13.9B · similar size |
Q4_K_M · 9.7 GB | 48 | Tight fit |
| Phi-4 14B 14.7B · similar size |
Q4_K_M · 10.4 GB | ~25 | CPU offload |
Gemma 3 12B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
8.3 GB | ~14 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
8.3 GB | 32 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
8.3 GB | 9.8 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
8.3 GB | 89 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
8.3 GB | 85 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
8.3 GB | 33 | Runs great |