What can NVIDIA GeForce RTX 3080 16GB (Mobile) run?
Build: NVIDIA GeForce RTX 3080 16GB (Mobile) + — + 32 GB RAM (windows)
Memory: 16 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
Runs comfortably97 models
Full-VRAM resident, with room for context. No compromises.
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 13.6 GBTTFT: instant919tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 13.6 GBTTFT: instant
919
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): ~61 ms (instant)
Quant: Q8_0Context: 8,192VRAM: 11.8 GBHeadroom: 4.2 GBTTFT: noticeableollama run llama3.1:8b39tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 11.8 GBHeadroom: 4.2 GBTTFT: noticeable
ollama run llama3.1:8b39
tok/s
Estimated
Weights
8.50 GB
KV cache
1.07 GB
Activations
0.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~819 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: noticeableollama run qwen3:8b69tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: noticeable
ollama run qwen3:8b69
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): ~819 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 12.4 GBTTFT: fast324tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 12.4 GBTTFT: fast
324
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): ~174 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 9.1 GBTTFT: fastollama run llama3.2:3b104tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 9.1 GBTTFT: fast
ollama run llama3.2:3b104
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): ~307 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 2.1 GBHeadroom: 13.9 GBTTFT: instant2042tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.1 GBHeadroom: 13.9 GBTTFT: instant
2042
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): ~28 ms (instant)
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: noticeableollama run qwen2.5:7b45tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: noticeable
ollama run qwen2.5:7b45
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GBTTFT: noticeableollama run deepseek-r1:7b79tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GBTTFT: noticeable
ollama run deepseek-r1:7b79
tok/s
Estimated
Weights
4.70 GB
KV cache
3.50 GB
Activations
0.24 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: noticeableollama run hermes3:8b69tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: noticeable
ollama run hermes3:8b69
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~819 ms (noticeable)
Quant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 7.6 GBTTFT: fastollama run gemma4:e4b78tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 7.6 GBTTFT: fast
ollama run gemma4:e4b78
tok/s
Estimated
Weights
4.40 GB
KV cache
2.00 GB
Activations
0.23 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~410 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 2.0 GBHeadroom: 14.0 GBTTFT: instant4083tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 2.0 GBHeadroom: 14.0 GBTTFT: instant
4083
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): ~14 ms (instant)
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 13.4 GBTTFT: fast501tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 13.4 GBTTFT: fast
501
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): ~113 ms (fast)
Runs with tradeoffs62 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 10.7 GBTTFT: slow- • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen3:30b18tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 10.7 GBTTFT: slow
- • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen3:30b18
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): ~3072 ms (slow)
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 11.3 GBTTFT: slow- • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen2.5-coder:32b17tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 11.3 GBTTFT: slow
- • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen2.5-coder:32b17
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): ~3277 ms (slow)
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: slow- • Partial CPU offload: ~38% of layers run on CPU
ollama run qwen3:32b17tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: slow
- • Partial CPU offload: ~38% of layers run on CPU
ollama run qwen3:32b17
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): ~3277 ms (slow)
Quant: Q4_K_MContext: 2,048VRAM: 24.6 GBHeadroom: 10.6 GBTTFT: slow- • Partial CPU offload: ~35% of layers run on CPU
ollama run gemma4:31b18tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 24.6 GBHeadroom: 10.6 GBTTFT: slow
- • Partial CPU offload: ~35% of layers run on CPU
ollama run gemma4:31b18
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): ~3174 ms (slow)
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: slow- • Partial CPU offload: ~38% of layers run on CPU
ollama run deepseek-r1:32b17tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: slow
- • Partial CPU offload: ~38% of layers run on CPU
ollama run deepseek-r1:32b17
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): ~3277 ms (slow)
Quant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 3.6 GBTTFT: slow- • Partial CPU offload: ~49% of layers run on CPU
ollama run gemma4:26b-moe21tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 3.6 GBTTFT: slow
- • Partial CPU offload: ~49% of layers run on CPU
ollama run gemma4:26b-moe21
tok/s
Estimated
Weights
16.00 GB
KV cache
13.00 GB
Activations
0.81 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~2662 ms (slow)
Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: noticeable- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run qwen3:14b39tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: noticeable
- • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run qwen3:14b39
tok/s
Estimated
Weights
8.40 GB
KV cache
1.75 GB
Activations
0.42 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1434 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 10.7 GBTTFT: slow- • Partial CPU offload: ~35% of layers run on CPU
ollama run nemotron3:nano18tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 10.7 GBTTFT: slow
- • Partial CPU offload: ~35% of layers run on CPU
ollama run nemotron3:nano18
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): ~3072 ms (slow)
What if you upgraded?
Hypothetical scenarios. We re-ran the compatibility engine for each.
+32 GB system RAM
Check the current price
Adds 32 GB to your CPU-offload working set. Helps when models don't quite fit in VRAM.
Unlocks: 78 new tradeoff
- • Qwen 3 30B-A3B
- • Llama 3.3 70B Instruct
- • Qwen 2.5 Coder 32B Instruct
- • Qwen 3 32B
Upgrade to NVIDIA RTX 2080 Ti 22GB (China-mod)
Check the current price
22 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~512 GB/s to ~616 GB/s.
Unlocks: 19 new comfortable
- • Qwen 3 14B
- • Phi-4 14B
- • Phi-4 Reasoning 14B
- • Mistral Nemo 12B Instruct
Add a second NVIDIA GeForce RTX 3080 16GB (Mobile)
Check the current price
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: 50 new comfortable
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen 3 32B
- • Gemma 4 31B Dense
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 (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (16 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.