Can I run Gemma 3 12B on the GeForce RTX 3060 12GB?
Runs greatQ4_K_M fits in VRAM with 3.0 GB to spare: Runs great, est. 32.2 tok/s (28.3–36.0, calibrated estimate ±12%).
12 GB VRAM · 360.0 GB/s · FP16 12.7 TFLOPS. Assumes 32 GB of DDR5-5600 system RAM, Windows with this GPU driving the display, 8k context and an f16 KV cache.
Every quant of Gemma 3 12B on the GeForce RTX 3060 12GB
| Quant | File size | Verdict | Speed | Memory | Runs as | Notes |
|---|---|---|---|---|---|---|
| Q2_K | 4.77 GB | Runs great | est. 47.5 tok/s41.8–53.2calibrated estimate ±12% | 6.5 / 12.0 GB | Full GPU | — |
| IQ4_XS | 6.55 GB | Runs great | est. 35.6 tok/s31.3–39.8calibrated estimate ±12% | 8.3 / 12.0 GB | Full GPU | — |
| Q4_K_Mbaseline | 7.30 GB | Runs great | est. 32.2 tok/s28.3–36.0calibrated estimate ±12% | 9.0 / 12.0 GB | Full GPU | — |
| Q8_0 | 12.51 GB | Runs slowly | est. 10.6 tok/s8.5–12.7calibrated estimate ±20% | 12.0 / 12.0 GB + 2.2 GB RAM | Partial offload | Less than 90% on the GPU — a GPU/CPU split is capped at Runs slowly |
Where the memory goes at Q4_K_M
- Weights
- 7.3 GB
- KV cache
- 0.5 GB
- Compute buffer
- 0.6 GB
- OS reserve
- 0.6 GB
- Free
- 3.0 GB
Context length vs. KV cache
| Context | KV f16 | KV q8_0 | KV q4_0 |
|---|---|---|---|
| 4k | 8.1 GBRuns great est. 33.3 tok/s29.3–37.3calibrated estimate ±12% | 8.0 GBRuns great est. 33.9 tok/s29.8–37.9calibrated estimate ±12% | 7.9 GBRuns great est. 34.2 tok/s30.1–38.3calibrated estimate ±12% |
| 8k | 8.4 GBRuns great est. 32.2 tok/s28.3–36.0calibrated estimate ±12% | 8.2 GBRuns great est. 33.2 tok/s29.2–37.2calibrated estimate ±12% | 8.0 GBRuns great est. 33.8 tok/s29.8–37.9calibrated estimate ±12% |
| 16k | 9.0 GBRuns great est. 30.1 tok/s26.5–33.7calibrated estimate ±12% | 8.5 GBRuns great est. 32.0 tok/s28.2–35.8calibrated estimate ±12% | 8.3 GBRuns great est. 33.1 tok/s29.2–37.1calibrated estimate ±12% |
| 32k | 10.2 GBRuns great est. 26.7 tok/s23.5–29.9calibrated estimate ±12% | 9.2 GBRuns great est. 29.8 tok/s26.2–33.4calibrated estimate ±12% | 8.7 GBRuns great est. 31.9 tok/s28.0–35.7calibrated estimate ±12% |
| 64k | 12.7 GBRuns slowly est. 11.9 tok/s9.6–14.3calibrated estimate ±20% | 10.7 GBRuns great est. 26.3 tok/s23.1–29.4calibrated estimate ±12% | 9.6 GBRuns great est. 29.6 tok/s26.0–33.1calibrated estimate ±12% |
| 128k | 17.6 GBRuns slowly est. 3.2 tok/s2.6–3.9calibrated estimate ±20% | 13.6 GBRuns slowly est. 8.9 tok/s7.1–10.6calibrated estimate ±20% | 11.4 GBRuns well est. 25.1 tok/s20.1–30.1calibrated estimate ±20% |
S = Runs great · A = Runs well · B = Runs slowly · F = Won't run
At Q4_K_M the verdict stays Runs great up to 32k context with an f16 KV cache, and up to 64k with q8_0.
Estimated speed
- Generation
- est. 32.2 tok/s (28.3–36.0, calibrated estimate ±12%)
- Prompt processing
- about 1,778 tok/s (1,067–2,489, rough estimate ±40%)
Measured on this exact combination
No public measurement for this exact combination yet; the numbers above are estimates.
If this is not enough
A larger model that also runs well on the GeForce RTX 3060 12GB
Runs wellQwen3.5 35B-A3B: Runs well, est. 20.4 tok/s (14.3–26.5, theoretical estimate ±30%)
How to run it
Commands for the Q4_K_M file. Both tools download from Hugging Face on first run.
File: google_gemma-3-12b-it-Q4_K_M.gguf (7.30 GB) from bartowski/google_gemma-3-12b-it-GGUF.
llama-server -hf bartowski/google_gemma-3-12b-it-GGUF:Q4_K_M -c 8192 -ngl all -fa on- -ngl all loads every layer on the GPU.
- -fa on enables flash attention (needed for KV cache quantization).
- --cache-type-k q8_0 --cache-type-v q8_0 shrinks the KV cache to 0.29 GB at 8k context.
PowerShell (quit the Ollama tray app first):
$env:OLLAMA_CONTEXT_LENGTH="8192"; ollama serve
ollama run hf.co/bartowski/google_gemma-3-12b-it-GGUF:Q4_K_M- Ollama defaults to 4k context on GPUs under 24 GB. Set OLLAMA_CONTEXT_LENGTH when starting the server, or /set parameter num_ctx inside the chat.
/set parameter num_ctx 8192
Related pages
Guide: How much VRAM do local LLMs need? 8–32 GB tiers (2026)
Other models on the GeForce RTX 3060 12GB
Gemma 3 12B on other hardware
Frequently asked questions
Can I run Gemma 3 12B on the GeForce RTX 3060 12GB?
Q4_K_M fits in VRAM with 3.0 GB to spare: Runs great, est. 32.2 tok/s (28.3–36.0, calibrated estimate ±12%). Q4_K_M needs 8.4 GB at 8k context; this setup has 11.4 GB of usable memory and 28.0 GB of free system RAM.
How much context can Gemma 3 12B use on the GeForce RTX 3060 12GB?
At Q4_K_M the verdict stays Runs great up to 32k context with an f16 KV cache (2.1 GB of KV) and up to 64k with a q8_0 KV cache (2.3 GB). The model supports up to 128k.
Which quant should I use, and how fast is it?
Q4_K_M (7.30 GB) is the recommended balance: Runs great, est. 32.2 tok/s (28.3–36.0, calibrated estimate ±12%). It is also the largest tracked file that gets this verdict.
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.