What can NVIDIA GeForce RTX 3090 run?

Build: RTX 3090 + Ryzen 9 5950X + 64GB DDR4 (used market)

Memory: 24 GB VRAM + 64 GB system RAM
Runner: llama.cpp / Ollama (CUDA)

Runs comfortably
20 models

Full-VRAM resident, with room for context. No compromises.

#1Gemma 3 1B
1B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 12.9 GB
ollama run gemma3:1b
1023
tok/s
E
Weights
0.60 GB
KV cache
0.50 GB
Activations
8.22 GB
Runtime
1.80 GB
#2Llama 3.2 1B Instruct
1B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 11.6 GBHeadroom: 12.4 GB
ollama run llama3.2:1b
581
tok/s
E
Weights
1.06 GB
KV cache
0.50 GB
Activations
8.25 GB
Runtime
1.80 GB
#3Gemma 4 E2B (Effective 2B)
2B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 13.2 GBHeadroom: 10.8 GB
ollama run gemma4:e2b
291
tok/s
E
Weights
2.13 GB
KV cache
1.00 GB
Activations
8.30 GB
Runtime
1.80 GB
#4Llama 3.2 3B Instruct
3B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.8 GBHeadroom: 9.2 GB
ollama run llama3.2:3b
194
tok/s
E
Weights
3.19 GB
KV cache
1.50 GB
Activations
8.35 GB
Runtime
1.80 GB
#5Phi-3.5 Vision
4.2B
phi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 14.8 GBHeadroom: 9.2 GB
244
tok/s
E
Weights
2.54 GB
KV cache
2.10 GB
Activations
8.32 GB
Runtime
1.80 GB
#6Phi-3.5 Mini Instruct
3.8B
phi
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 16.1 GBHeadroom: 7.9 GB
ollama run phi3.5:3.8b
153
tok/s
E
Weights
4.04 GB
KV cache
1.90 GB
Activations
8.39 GB
Runtime
1.80 GB
#7Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 7.5 GB
ollama run gemma4:e4b
145
tok/s
E
Weights
4.25 GB
KV cache
2.00 GB
Activations
8.40 GB
Runtime
1.80 GB
#8Qwen 3 4B
4B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 7.5 GB
ollama run qwen3:4b
145
tok/s
E
Weights
4.25 GB
KV cache
2.00 GB
Activations
8.40 GB
Runtime
1.80 GB
#9Gemma 3 4B
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 7.5 GB
ollama run gemma3:4b
145
tok/s
E
Weights
4.25 GB
KV cache
2.00 GB
Activations
8.40 GB
Runtime
1.80 GB
#10Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 19.1 GBHeadroom: 4.9 GB
128
tok/s
E
Weights
4.83 GB
KV cache
4.00 GB
Activations
8.43 GB
Runtime
1.80 GB
#11Mistral 7B Instruct v0.3
7B
mistral
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 18.5 GBHeadroom: 5.5 GB
ollama run mistral:7b
128
tok/s
E
Weights
4.81 GB
KV cache
3.50 GB
Activations
8.43 GB
Runtime
1.80 GB
#12CodeGemma 7B
7B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 6.1 GB
ollama run codegemma:7b
146
tok/s
E
Weights
4.23 GB
KV cache
3.50 GB
Activations
8.40 GB
Runtime
1.80 GB

Runs with tradeoffs
32 models

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

Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 58.5 GBHeadroom: 3.9 GB
  • Partial CPU offload: ~59% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30b
1
tok/s
E
Weights
31.88 GB
KV cache
15.00 GB
Activations
9.79 GB
Runtime
1.80 GB
Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 47.8 GBHeadroom: 14.6 GB
  • Partial CPU offload: ~50% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen2.5-coder:32b
1
tok/s
E
Weights
34.00 GB
KV cache
2.15 GB
Activations
9.89 GB
Runtime
1.80 GB
Llama 3.3 70B Instruct
70B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 57.1 GBHeadroom: 5.3 GB
  • Partial CPU offload: ~58% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run llama3.3:70b
1
tok/s
E
Weights
42.26 GB
KV cache
2.68 GB
Activations
10.31 GB
Runtime
1.80 GB
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 61.7 GBHeadroom: 0.7 GB
  • Partial CPU offload: ~61% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32b
1
tok/s
E
Weights
34.00 GB
KV cache
16.00 GB
Activations
9.89 GB
Runtime
1.80 GB
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 60.1 GBHeadroom: 2.3 GB
  • Partial CPU offload: ~60% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run gemma4:31b
1
tok/s
E
Weights
32.94 GB
KV cache
15.50 GB
Activations
9.84 GB
Runtime
1.80 GB
Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 22.9 GBHeadroom: 1.1 GB
  • Tight VRAM fit — only 1.1 GB headroom left for context growth
ollama run qwen3:8b
73
tok/s
E
Weights
8.50 GB
KV cache
4.00 GB
Activations
8.62 GB
Runtime
1.80 GB
DeepSeek R1 Distill Llama 70B
70B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 57.0 GBHeadroom: 5.4 GB
  • Partial CPU offload: ~58% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:70b
1
tok/s
E
Weights
42.26 GB
KV cache
8.75 GB
Activations
4.16 GB
Runtime
1.80 GB
DeepSeek R1 Distill Qwen 32B
32B
deepseek
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 61.7 GBHeadroom: 0.7 GB
  • Partial CPU offload: ~61% of layers run on CPU
  • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:32b
1
tok/s
E
Weights
34.00 GB
KV cache
16.00 GB
Activations
9.89 GB
Runtime
1.80 GB

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: 33 new tradeoff

  • Qwen 3 30B-A3B
  • Qwen 2.5 Coder 32B Instruct
  • Llama 3.3 70B Instruct
  • Qwen 3 32B

Upgrade to NVIDIA RTX 5000 Ada Generation

see current pricing

32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~? GB/s to ~? GB/s.

Unlocks: 15 new comfortable

  • DeepSeek R1 Distill Qwen 7B
  • Qwen 3 8B
  • Hermes 3 Llama 3.1 8B
  • Gemma 2 9B Instruct

Add a second NVIDIA GeForce RTX 3090

~$899

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: 16 new comfortable

  • DeepSeek R1 Distill Qwen 7B
  • Qwen 3 8B
  • Hermes 3 Llama 3.1 8B
  • Gemma 2 9B Instruct

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.

Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

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

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

GLM-5
200B
other
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

DeepSeek V3 (671B MoE)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

How to read these numbers

M
Measured — we ran this exact combo on owner hardware.

~
Extrapolated — predicted from a measured benchmark on similar-bandwidth hardware.

E
Estimated — pure formula based on VRAM bandwidth and model architecture.

Full methodology →

Want a specific benchmark we don't have? Email benchmarks@runlocalai.co and we'll prioritize it.