What can NVIDIA GeForce RTX 3060 12GB run?
Build: NVIDIA GeForce RTX 3060 12GB + — + 32 GB RAM (windows)
Memory: 12 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
Runs comfortably67 models
Full-VRAM resident, with room for context. No compromises.
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 9.6 GBTTFT: fast646tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 9.6 GBTTFT: fast
646
tok/s
Estimated
Weights
0.30 GB
KV cache
0.30 GB
Activations
0.02 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~121 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 5.1 GBTTFT: noticeableollama run llama3.2:3b73tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 5.1 GBTTFT: noticeable
ollama run llama3.2:3b73
tok/s
Estimated
Weights
3.40 GB
KV cache
1.50 GB
Activations
0.18 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 8.4 GBTTFT: fast228tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 8.4 GBTTFT: fast
228
tok/s
Estimated
Weights
0.90 GB
KV cache
0.85 GB
Activations
0.05 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Quant: Q5_K_MContext: 8,192VRAM: 7.9 GBHeadroom: 4.1 GBTTFT: noticeableollama run qwen2.5:7b49tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 7.9 GBHeadroom: 4.1 GBTTFT: noticeable
ollama run qwen2.5:7b49
tok/s
Estimated
Weights
5.40 GB
KV cache
0.47 GB
Activations
0.28 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1411 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 2.1 GBHeadroom: 9.9 GBTTFT: instant1435tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.1 GBHeadroom: 9.9 GBTTFT: instant
1435
tok/s
Estimated
Weights
0.16 GB
KV cache
0.14 GB
Activations
0.02 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~54 ms (instant)
Quant: Q4_K_MContext: 8,192VRAM: 2.0 GBHeadroom: 10.0 GBTTFT: instant2871tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.0 GBHeadroom: 10.0 GBTTFT: instant
2871
tok/s
Estimated
Weights
0.08 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~27 ms (instant)
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 9.4 GBTTFT: fast352tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 9.4 GBTTFT: fast
352
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~222 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 8.0 GBTTFT: fast194tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 8.0 GBTTFT: fast
194
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~403 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 3.7 GBHeadroom: 8.3 GBTTFT: fastollama run llama3.2:1b220tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 3.7 GBHeadroom: 8.3 GBTTFT: fast
ollama run llama3.2:1b220
tok/s
Estimated
Weights
1.30 GB
KV cache
0.50 GB
Activations
0.07 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~202 ms (fast)
Quant: Q4_K_MContext: 4,096VRAM: 7.6 GBHeadroom: 4.4 GBTTFT: noticeable55tok/sEstimated
Quant: Q4_K_MContext: 4,096VRAM: 7.6 GBHeadroom: 4.4 GBTTFT: noticeable
55
tok/s
Estimated
Weights
3.90 GB
KV cache
1.75 GB
Activations
0.20 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1411 ms (noticeable)
Quant: Q8_0Context: 8,192VRAM: 5.1 GBHeadroom: 6.9 GBTTFT: fastollama run gemma4:e2b110tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 5.1 GBHeadroom: 6.9 GBTTFT: fast
ollama run gemma4:e2b110
tok/s
Estimated
Weights
2.20 GB
KV cache
1.00 GB
Activations
0.12 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~403 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 7.4 GBTTFT: fastollama run alibayram/kumru:latest161tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 7.4 GBTTFT: fast
ollama run alibayram/kumru:latest161
tok/s
Estimated
Weights
1.50 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~484 ms (fast)
Runs with tradeoffs166 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q5_K_MContext: 8,192VRAM: 8.9 GBHeadroom: 3.1 GBTTFT: noticeable- • Tight VRAM fit — only 3.1 GB headroom left for context growth
ollama run llama3.1:8b43tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 8.9 GBHeadroom: 3.1 GBTTFT: noticeable
- • Tight VRAM fit — only 3.1 GB headroom left for context growth
ollama run llama3.1:8b43
tok/s
Estimated
Weights
5.70 GB
KV cache
1.07 GB
Activations
0.29 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1613 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 6.7 GBTTFT: slow- • Partial CPU offload: ~51% of layers run on CPU
ollama run qwen3:30b13tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 6.7 GBTTFT: slow
- • Partial CPU offload: ~51% of layers run on CPU
ollama run qwen3:30b13
tok/s
Estimated
Weights
18.00 GB
KV cache
3.75 GB
Activations
0.90 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~6047 ms (slow)
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 7.3 GBTTFT: slow- • Partial CPU offload: ~50% of layers run on CPU
ollama run qwen2.5-coder:32b12tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 7.3 GBTTFT: slow
- • Partial CPU offload: ~50% of layers run on CPU
ollama run qwen2.5-coder:32b12
tok/s
Estimated
Weights
19.00 GB
KV cache
2.15 GB
Activations
0.96 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~6450 ms (slow)
Quant: Q4_K_MContext: 2,048VRAM: 23.0 GBHeadroom: 8.2 GBTTFT: slow- • Partial CPU offload: ~48% of layers run on CPU
ollama run qwen3.6:27b14tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 23.0 GBHeadroom: 8.2 GBTTFT: slow
- • Partial CPU offload: ~48% of layers run on CPU
ollama run qwen3.6:27b14
tok/s
Estimated
Weights
17.00 GB
KV cache
3.38 GB
Activations
0.85 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~5443 ms (slow)
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 5.4 GBTTFT: slow- • Partial CPU offload: ~53% of layers run on CPU
ollama run qwen3:32b12tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 5.4 GBTTFT: slow
- • Partial CPU offload: ~53% of layers run on CPU
ollama run qwen3:32b12
tok/s
Estimated
Weights
19.00 GB
KV cache
4.00 GB
Activations
0.95 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~6450 ms (slow)
Quant: Q4_K_MContext: 2,048VRAM: 24.6 GBHeadroom: 6.6 GBTTFT: slow- • Partial CPU offload: ~51% of layers run on CPU
ollama run gemma4:31b13tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 24.6 GBHeadroom: 6.6 GBTTFT: slow
- • Partial CPU offload: ~51% of layers run on CPU
ollama run gemma4:31b13
tok/s
Estimated
Weights
18.00 GB
KV cache
3.88 GB
Activations
0.90 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~6249 ms (slow)
Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 1.2 GBTTFT: noticeable- • Tight VRAM fit — only 1.2 GB headroom left for context growth
ollama run qwen3:8b48tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 1.2 GBTTFT: noticeable
- • Tight VRAM fit — only 1.2 GB headroom left for context growth
ollama run qwen3:8b48
tok/s
Estimated
Weights
4.80 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1613 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 11.3 GBHeadroom: 0.7 GBTTFT: slow- • Tight VRAM fit — only 0.7 GB headroom left for context growth
ollama run gemma4:12b32tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 11.3 GBHeadroom: 0.7 GBTTFT: slow
- • Tight VRAM fit — only 0.7 GB headroom left for context growth
ollama run gemma4:12b32
tok/s
Estimated
Weights
7.60 GB
KV cache
1.50 GB
Activations
0.38 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~2419 ms (slow)
What if you upgraded?
Hypothetical scenarios. We re-ran the compatibility engine for each.
+32 GB system RAM
~$80–150
Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.
Unlocks: 174 new tradeoff
- • Llama 3.1 8B Instruct
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
Upgrade to NVIDIA GeForce RTX 4070 Ti Super
~$829
16 GB VRAM (vs your 12 GB) plus a bandwidth jump from ~360 GB/s to ~672 GB/s.
Unlocks: 75 new comfortable
- • Llama 3.1 8B Instruct
- • Qwen 3 8B
- • DeepSeek R1 Distill Qwen 7B
- • Hermes 3 Llama 3.1 8B
Add a second NVIDIA GeForce RTX 3060 12GB
~$249
Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.
Unlocks: 117 new comfortable
- • Llama 3.1 8B Instruct
- • Qwen 3 8B
- • Gemma 4 12B
- • Qwen3.5 9B
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Won't runtop 5 popular models
Need more memory than you have. Shown for orientation.
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (12 GB) + 60% of system RAM (19 GB) combined.
—
How to read these numbers
Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.