What can NVIDIA GeForce RTX 5090 run for agents?
Build: RTX 5090 + Ryzen 9 9950X + 64GB DDR5
Memory: 32 GB VRAM + 64 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
Runs comfortably152 models
Ranked by fit for agents use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q8_0Context: 8,192VRAM: 14.7 GBHeadroom: 17.3 GBTTFT: fastollama run hermes3:8b137tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 14.7 GBHeadroom: 17.3 GBTTFT: fast
ollama run hermes3:8b137
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~164 ms (fast)
Quant: Q8_0Context: 8,192VRAM: 25.3 GBHeadroom: 6.7 GBTTFT: fastollama run qwen2.5:14b78tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 25.3 GBHeadroom: 6.7 GBTTFT: fast
ollama run qwen2.5:14b78
tok/s
Estimated
Weights
15.70 GB
KV cache
7.00 GB
Activations
0.79 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~287 ms (fast)
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 7.5 GBTTFT: noticeableollama run qwen3:30b64tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 7.5 GBTTFT: noticeable
ollama run qwen3:30b64
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): ~614 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 25.5 GBHeadroom: 6.5 GBTTFT: noticeableollama run qwen3-coder:30b64tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.5 GBHeadroom: 6.5 GBTTFT: noticeable
ollama run qwen3-coder:30b64
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): ~614 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 8.1 GBTTFT: noticeableollama run qwen2.5-coder:32b60tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 8.1 GBTTFT: noticeable
ollama run qwen2.5-coder:32b60
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): ~655 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 6.2 GBTTFT: noticeableollama run qwen3:32b60tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 6.2 GBTTFT: noticeable
ollama run qwen3:32b60
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): ~655 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 6.2 GBTTFT: noticeableollama run qwen2.5:32b60tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 6.2 GBTTFT: noticeable
ollama run qwen2.5:32b60
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): ~655 ms (noticeable)
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 21.2 GBTTFT: fastollama run qwen2.5:7b157tok/sEstimated
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 21.2 GBTTFT: fast
ollama run qwen2.5:7b157
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): ~143 ms (fast)
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 7.5 GBTTFT: noticeableollama run nemotron3:nano64tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 24.5 GBHeadroom: 7.5 GBTTFT: noticeable
ollama run nemotron3:nano64
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): ~614 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 25.5 GBHeadroom: 6.5 GBTTFT: noticeableollama run north-mini-code-1.064tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.5 GBHeadroom: 6.5 GBTTFT: noticeable
ollama run north-mini-code-1.064
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): ~614 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 25.6 GBHeadroom: 6.4 GBTTFT: noticeableollama run glm-4.7-flash62tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 25.6 GBHeadroom: 6.4 GBTTFT: noticeable
ollama run glm-4.7-flash62
tok/s
Estimated
Weights
19.00 GB
KV cache
3.88 GB
Activations
0.95 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~635 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 26.9 GBHeadroom: 5.1 GBTTFT: noticeableollama run laguna-xs-2.158tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 26.9 GBHeadroom: 5.1 GBTTFT: noticeable
ollama run laguna-xs-2.158
tok/s
Estimated
Weights
20.00 GB
KV cache
4.13 GB
Activations
1.00 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~676 ms (noticeable)
Runs with tradeoffs43 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast- • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run dolphin-mistral:24b80tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast
- • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run dolphin-mistral:24b80
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): ~492 ms (fast)
Quant: Q4_K_MContext: 2,048VRAM: 28.2 GBHeadroom: 3.8 GBTTFT: noticeable- • Tight VRAM fit — only 3.8 GB headroom left for context growth
ollama run ornith:35b55tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 28.2 GBHeadroom: 3.8 GBTTFT: noticeable
- • Tight VRAM fit — only 3.8 GB headroom left for context growth
ollama run ornith:35b55
tok/s
Estimated
Weights
21.00 GB
KV cache
4.38 GB
Activations
1.05 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast- • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run mistral-small:24b80tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast
- • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run mistral-small:24b80
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): ~492 ms (fast)
Quant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 0.4 GBTTFT: noticeable- • Tight VRAM fit — only 0.4 GB headroom left for context growth
ollama run gemma4:26b-moe74tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 0.4 GBTTFT: noticeable
- • Tight VRAM fit — only 0.4 GB headroom left for context growth
ollama run gemma4:26b-moe74
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): ~532 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 31.4 GBHeadroom: 0.6 GBTTFT: noticeable- • Tight VRAM fit — only 0.6 GB headroom left for context growth
ollama run qwen3.6:35b-a3b55tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 31.4 GBHeadroom: 0.6 GBTTFT: noticeable
- • Tight VRAM fit — only 0.6 GB headroom left for context growth
ollama run qwen3.6:35b-a3b55
tok/s
Estimated
Weights
24.00 GB
KV cache
4.38 GB
Activations
1.20 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 31.4 GBHeadroom: 0.6 GBTTFT: noticeable- • Tight VRAM fit — only 0.6 GB headroom left for context growth
ollama run qwen3.5:35b-a3b55tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 31.4 GBHeadroom: 0.6 GBTTFT: noticeable
- • Tight VRAM fit — only 0.6 GB headroom left for context growth
ollama run qwen3.5:35b-a3b55
tok/s
Estimated
Weights
24.00 GB
KV cache
4.38 GB
Activations
1.20 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~717 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 52.6 GBHeadroom: 17.8 GBTTFT: noticeable- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:70b2tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 52.6 GBHeadroom: 17.8 GBTTFT: noticeable
- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:70b2
tok/s
Estimated
Weights
40.00 GB
KV cache
8.75 GB
Activations
2.00 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1434 ms (noticeable)
Quant: Q4_K_MContext: 2,048VRAM: 52.6 GBHeadroom: 17.8 GBTTFT: noticeable- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run llama3.1:70b2tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 52.6 GBHeadroom: 17.8 GBTTFT: noticeable
- • Partial CPU offload: ~39% of layers run on CPU
- • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run llama3.1:70b2
tok/s
Estimated
Weights
40.00 GB
KV cache
8.75 GB
Activations
2.00 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1434 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, 48 new tradeoff
- • Qwen 3 0.6B
- • Llama 3.2 3B Instruct
- • Qwen 3 1.7B
- • Gemma 3 270M
Upgrade to NVIDIA A100 40GB
see current pricing
40 GB VRAM (vs your 32 GB) plus a bandwidth jump from ~1792 GB/s to ~1555 GB/s.
Unlocks: 85 new comfortable
- • Qwen 3 0.6B
- • Qwen3.6 35B-A3B
- • Llama 3.2 3B Instruct
- • Qwen 3 1.7B
Add a second NVIDIA GeForce RTX 5090
~$2499
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: 103 new comfortable
- • Qwen 3 0.6B
- • Llama 3.3 70B Instruct
- • DeepSeek R1 Distill Llama 70B
- • Qwen3.6 35B-A3B
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 (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (32 GB) + 60% of system RAM (38 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.