What can NVIDIA GeForce RTX 5080 run for reasoning?

Build: NVIDIA GeForce RTX 5080 + — + 32 GB RAM (windows)

Memory: 16 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
78 models

Ranked by fit for reasoning use case + predicted speed. Click a row for VRAM breakdown.

#1DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GBTTFT: fast
ollama run deepseek-r1:7b
148
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): ~320 ms (fast)
Model details →
#2Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: fast
129
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): ~366 ms (fast)
Model details →
#3RefinedNeuro RN TR R1
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: fast
ollama run RefinedNeuro/RN_TR_R1:latest
129
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): ~366 ms (fast)
Model details →Reference measurement: 133.6 tok/s at 2,048 context · ollama-local-api · settings may differ →
#4DeepSeek R1 Distill Llama 8B
8B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 5.3 GBTTFT: fast
129
tok/s
Estimated
Weights
4.70 GB
KV cache
4.00 GB
Activations
0.24 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~366 ms (fast)
Model details →
#5NVIDIA Nemotron Nano 9B v2 Japanese
9B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.6 GBHeadroom: 4.4 GBTTFT: fast
115
tok/s
Estimated
Weights
5.00 GB
KV cache
4.50 GB
Activations
0.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~411 ms (fast)
Model details →
#6EXAONE Deep 7.8B
7.8B
other
Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 5.8 GBTTFT: fast
133
tok/s
Estimated
Weights
4.30 GB
KV cache
3.90 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~357 ms (fast)
Model details →
#7RefinedNeuro RN TR R2
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: fast
ollama run RefinedNeuro/RN_TR_R2:latest
129
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): ~366 ms (fast)
Model details →Reference measurement: 133.4 tok/s at 2,048 context · ollama-local-api · settings may differ →
#8InternLM 2.5 7B Chat
7B
internlm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast
148
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): ~320 ms (fast)
Model details →
#9Qwen 2.5 Math 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 8.2 GBHeadroom: 7.8 GBTTFT: fast
148
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): ~320 ms (fast)
Model details →
#10Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast
148
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): ~320 ms (fast)
Model details →
#11Nemotron 3 Nano 9B
9B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.9 GBHeadroom: 4.1 GBTTFT: fast
115
tok/s
Estimated
Weights
5.30 GB
KV cache
4.50 GB
Activations
0.27 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~411 ms (fast)
Model details →
#12Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 5.2 GBTTFT: fast
ollama run qwen3:8b
129
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): ~366 ms (fast)
Model details →

Runs with tradeoffs
94 models

Tight VRAM, partial CPU offload, or context-limited.

Phi-4 Reasoning 14B
14B
phi
Commercial OK
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 phi4-reasoning:14b
74
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): ~640 ms (noticeable)
Model details →
DeepSeek R1 Distill Qwen 14B
14B
deepseek
Commercial OK
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 deepseek-r1:14b
74
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): ~640 ms (noticeable)
Model details →
DeepSeek V3 Lite (16B MoE)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 13.8 GBHeadroom: 2.2 GBTTFT: fast
  • • Tight VRAM fit — only 2.2 GB headroom left for context growth
431
tok/s
Estimated
Weights
9.50 GB
KV cache
2.00 GB
Activations
0.48 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~110 ms (fast)
Model details →
DeepSeek R1 Distill Mistral 24B
24B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 6.7 GBTTFT: noticeable
  • • Partial CPU offload: ~44% of layers run on CPU
43
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): ~1097 ms (noticeable)
Model details →
Omni 31B Turkish Reasoning
31B
other
Quant: Q4_K_MContext: 2,048VRAM: 23.6 GBHeadroom: 11.6 GBTTFT: noticeable
  • • Partial CPU offload: ~32% of layers run on CPU
33
tok/s
Estimated
Weights
17.10 GB
KV cache
3.88 GB
Activations
0.86 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1417 ms (noticeable)
Model details →
DeepSeek R1 Distill Qwen 32B
32B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: noticeable
  • • Partial CPU offload: ~38% of layers run on CPU
ollama run deepseek-r1:32b
32
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): ~1463 ms (noticeable)
Model details →
QwQ 32B Preview
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GBTTFT: noticeable
  • • Partial CPU offload: ~38% of layers run on CPU
ollama run qwq:32b
32
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): ~1463 ms (noticeable)
Model details →
Phi-4 14B
14B
phi
Commercial OK
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 phi4:14b
74
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): ~640 ms (noticeable)
Model details →

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
Shop this upgrade↗

Upgrade to NVIDIA RTX 2080 Ti 22GB (China-mod)

~$350

22 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~960 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
Shop this upgrade↗

Add a second NVIDIA GeForce RTX 5080

~$1199

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
Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—
DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 GB) + 60% of system RAM (19 GB) combined.

—
Llama 4 Scout
109B
llama
Commercial OK

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.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.