What can NVIDIA GeForce RTX 5080 run for creative?

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
75 models

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

#1Hermes 3 Llama 3.1 8B
8B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 5.0 GBTTFT: fast
ollama run hermes3:8b
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 →
#2Dolphin 3.0 Llama 3.2 3B
3B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 10.8 GBTTFT: fast
345
tok/s
Estimated
Weights
1.80 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~137 ms (fast)
Model details →
#3Hermes 3 Llama 3.2 3B
3B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 10.8 GBTTFT: fast
345
tok/s
Estimated
Weights
1.80 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~137 ms (fast)
Model details →
#4Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 7.6 GBTTFT: fast
ollama run gemma4:e4b
147
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): ~183 ms (fast)
Model details →
#5Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 12.0 GBTTFT: instant
517
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): ~91 ms (instant)
Model details →
#6Gemma 3 4B
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 8.4 GBHeadroom: 7.6 GBTTFT: fast
ollama run gemma3:4b
147
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): ~183 ms (fast)
Model details →
#7Gemma 4 E2B (Effective 2B)
2B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 5.1 GBHeadroom: 10.9 GBTTFT: instant
ollama run gemma4:e2b
294
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): ~91 ms (instant)
Model details →
#8CodeGemma 7B
7B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 6.3 GBTTFT: fast
ollama run codegemma:7b
148
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~320 ms (fast)
Model details →
#9Turkish Gemma 9B T1
9B
gemma
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 →
#10PaliGemma 2 3B
3B
gemma
Commercial OK
Quant: BF16Context: 8,192VRAM: 9.6 GBHeadroom: 6.4 GBTTFT: fast
104
tok/s
Estimated
Weights
6.00 GB
KV cache
1.50 GB
Activations
0.31 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~137 ms (fast)
Model details →
#11Qwen 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 →
#12Llama 3.2 3B Instruct
3B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 9.1 GBTTFT: fast
ollama run llama3.2:3b
196
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): ~137 ms (fast)
Model details →

Runs with tradeoffs
46 models

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

Gemma 2 9B Instruct
9B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.4 GBHeadroom: 3.6 GBTTFT: fast
  • • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run gemma2:9b
115
tok/s
Estimated
Weights
5.80 GB
KV cache
4.50 GB
Activations
0.30 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~411 ms (fast)
Model details →
YTU Turkish Gemma 9B v0.1
9.2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 12.5 GBHeadroom: 3.5 GBTTFT: fast
  • • Tight VRAM fit — only 3.5 GB headroom left for context growth
ollama run alibayram/turkish-gemma-9b-v0.1:latest
112
tok/s
Estimated
Weights
5.80 GB
KV cache
4.60 GB
Activations
0.30 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~421 ms (fast)
Model details →
Dolphin 3.0 Mistral 24B
24B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 6.7 GBTTFT: noticeable
  • • Partial CPU offload: ~44% of layers run on CPU
ollama run dolphin-mistral:24b
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 →
Gemma 3 12B
12B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 15.5 GBHeadroom: 0.5 GBTTFT: noticeable
  • • Tight VRAM fit — only 0.5 GB headroom left for context growth
ollama run gemma3:12b
86
tok/s
Estimated
Weights
7.30 GB
KV cache
6.00 GB
Activations
0.37 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~549 ms (noticeable)
Model details →
DeepSeek V2 Lite Chat
15.7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.8 GBHeadroom: 3.2 GBTTFT: fast
  • • Tight VRAM fit — only 3.2 GB headroom left for context growth
431
tok/s
Estimated
Weights
8.60 GB
KV cache
1.96 GB
Activations
0.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~110 ms (fast)
Model details →
DeepSeek MoE 16B Base
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 15.8 GBHeadroom: 0.2 GBTTFT: fast
  • • Tight VRAM fit — only 0.2 GB headroom left for context growth
431
tok/s
Estimated
Weights
9.50 GB
KV cache
4.00 GB
Activations
0.48 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~110 ms (fast)
Model details →
GLM-4 9B
9B
glm
Quant: Q4_K_MContext: 8,192VRAM: 12.1 GBHeadroom: 3.9 GBTTFT: fast
  • • Tight VRAM fit — only 3.9 GB headroom left for context growth
115
tok/s
Estimated
Weights
5.50 GB
KV cache
4.50 GB
Activations
0.28 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~411 ms (fast)
Model details →
Falcon 3 10B
10B
falcon
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 13.1 GBHeadroom: 2.9 GBTTFT: fast
  • • Tight VRAM fit — only 2.9 GB headroom left for context growth
103
tok/s
Estimated
Weights
6.00 GB
KV cache
5.00 GB
Activations
0.31 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~457 ms (fast)
Model details →

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: 13 new comfortable, 57 new tradeoff

  • • Qwen 3 0.6B
  • • Gemma 3 270M
  • • SmolLM2 135M Instruct
  • • TinyLlama 1.1B Chat v1.0
Shop this upgrade↗

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 ~960 GB/s to ~616 GB/s.

Unlocks: 32 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 14B
  • • Gemma 3 270M
  • • Phi-4 14B

Add a second NVIDIA GeForce RTX 5080

Launch MSRP $999 (2025). 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: 53 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen 3 32B
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 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.

—
DeepSeek V4 Flash (284B MoE)
284B
deepseek
Commercial OK

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

—
Cloud GPU rental

Not enough VRAM for these models? Rent a GPU by the hour

The models above need more memory than 16 GB VRAM + 32 GB system RAM. You can rent a GPU with enough VRAM by the hour to run one of them, or to test it before you buy hardware. For daily use, owning a card usually costs less over time.

RunPod

billed per GPU-hour

Hourly GPU pods, in community-cloud and secure-cloud tiers.

The two tiers run on different hosts and terms. Check which tier a pod is on before a long job.

Rent on RunPod

Vast.ai

billed per GPU-hour

Marketplace of host-listed GPUs; price and reliability vary by host.

Host quality varies. Filter for verified hosts and check the host's reliability before a long run.

Rent on Vast.ai

Referral links: RunLocalAI may earn a commission or account credits if you sign up and rent, at no extra cost to you. Hourly rates and which GPUs are listed change all the time, so check the provider's page before you start. Editorial opinions are independent of the referral relationship; see how we make money.

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.