What can NVIDIA GeForce RTX 4080 Super run for agents?
Build: RTX 4080 Super + i7-14700K + 32GB DDR5
Memory: 16 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
Runs comfortably78 models
Ranked by fit for agents use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: fastollama run hermes3:8b99tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: fast
ollama run hermes3:8b99
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): ~392 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: fastollama run qwen2.5:7b64tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: fast
ollama run qwen2.5:7b64
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): ~343 ms (fast)
Quant: Q5_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 5.3 GBTTFT: fastollama run mistral:7b99tok/sEstimated
Quant: Q5_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 5.3 GBTTFT: fast
ollama run mistral:7b99
tok/s
Estimated
Weights
5.10 GB
KV cache
3.50 GB
Activations
0.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: fast99tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: fast
99
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): ~392 ms (fast)
Quant: Q4_K_MContext: 2,048VRAM: 11.7 GBHeadroom: 4.3 GBTTFT: noticeableollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M65tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 11.7 GBHeadroom: 4.3 GBTTFT: noticeable
ollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M65
tok/s
Estimated
Weights
8.00 GB
KV cache
1.52 GB
Activations
0.40 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~596 ms (noticeable)
Quant: Q8_0Context: 8,192VRAM: 11.8 GBHeadroom: 4.2 GBTTFT: fastollama run llama3.1:8b56tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 11.8 GBHeadroom: 4.2 GBTTFT: fast
ollama run llama3.1:8b56
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): ~392 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 4.9 GBTTFT: fastollama run dolphin3:8b99tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 4.9 GBTTFT: fast
ollama run dolphin3:8b99
tok/s
Estimated
Weights
5.00 GB
KV cache
4.00 GB
Activations
0.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~392 ms (fast)
Quant: Q4_K_MContext: 4,096VRAM: 8.2 GBHeadroom: 7.8 GBTTFT: fast113tok/sEstimated
Quant: Q4_K_MContext: 4,096VRAM: 8.2 GBHeadroom: 7.8 GBTTFT: fast
113
tok/s
Estimated
Weights
4.40 GB
KV cache
1.75 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast113tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast
113
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast113tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast
113
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GBTTFT: fast113tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 10.1 GBHeadroom: 5.9 GBTTFT: fast
113
tok/s
Estimated
Weights
4.60 GB
KV cache
3.50 GB
Activations
0.24 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast113tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast
113
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Runs with tradeoffs94 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 12.9 GBHeadroom: 3.1 GBTTFT: noticeable- • Tight VRAM fit — only 3.1 GB headroom left for context growth
ollama run qwen2.5:14b57tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 12.9 GBHeadroom: 3.1 GBTTFT: noticeable
- • Tight VRAM fit — only 3.1 GB headroom left for context growth
ollama run qwen2.5:14b57
tok/s
Estimated
Weights
8.90 GB
KV cache
1.75 GB
Activations
0.45 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~687 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 12.2 GBHeadroom: 3.8 GBTTFT: fast- • Tight VRAM fit — only 3.8 GB headroom left for context growth
ollama run ornith:9b88tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 12.2 GBHeadroom: 3.8 GBTTFT: fast
- • Tight VRAM fit — only 3.8 GB headroom left for context growth
ollama run ornith:9b88
tok/s
Estimated
Weights
5.60 GB
KV cache
4.50 GB
Activations
0.29 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~441 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 6.7 GBTTFT: noticeable- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run dolphin-mistral:24b4tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 6.7 GBTTFT: noticeable
- • Partial CPU offload: ~44% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run dolphin-mistral:24b4
tok/s
Estimated
Weights
14.00 GB
KV cache
12.00 GB
Activations
0.71 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1177 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 10.7 GBTTFT: noticeable- • Partial CPU offload: ~35% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30b4tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 10.7 GBTTFT: noticeable
- • Partial CPU offload: ~35% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30b4
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): ~1471 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 11.3 GBTTFT: noticeable- • Partial CPU offload: ~33% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen2.5-coder:32b4tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 11.3 GBTTFT: noticeable
- • Partial CPU offload: ~33% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen2.5-coder:32b4
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): ~1569 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 25.5 GBHeadroom: 9.7 GBTTFT: noticeable- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3-coder:30b4tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.5 GBHeadroom: 9.7 GBTTFT: noticeable
- • Partial CPU offload: ~37% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3-coder:30b4
tok/s
Estimated
Weights
19.00 GB
KV cache
3.75 GB
Activations
0.95 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1471 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: noticeable- • Partial CPU offload: ~38% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32b3tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: noticeable
- • Partial CPU offload: ~38% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32b3
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): ~1569 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: noticeable- • Partial CPU offload: ~38% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen2.5:32b3tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: noticeable
- • Partial CPU offload: ~38% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen2.5:32b3
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): ~1569 ms (noticeable)
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: 64 new comfortable, 112 new tradeoff
- • Qwen 3 0.6B
- • Llama 3.2 3B Instruct
- • Qwen 3 1.7B
- • Gemma 3 270M
Upgrade to NVIDIA RTX 2080 Ti 22GB (China-mod)
~$350
22 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~736 GB/s to ~616 GB/s.
Unlocks: 91 new comfortable
- • Qwen 3 0.6B
- • Gemma 4 12B
- • Qwen3.5 9B
- • Llama 3.2 3B Instruct
Add a second NVIDIA GeForce RTX 4080 Super
~$1099
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: 138 new comfortable
- • Qwen 3 0.6B
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
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.