What can NVIDIA GeForce RTX 5070 Ti run locally?

0 models fit comfortably on NVIDIA GeForce RTX 5070 Ti with 32 GB system RAM. 11 more run with tradeoffs. Top pick: see results below.

What's the recommended runner for this hardware?

llama.cpp / Ollama (CUDA). This is the runner that gives best tokens-per-second on NVIDIA GeForce RTX 5070 Ti based on windows support and the GPU backend.

What can NVIDIA GeForce RTX 5070 Ti run for vision?

Build: NVIDIA GeForce RTX 5070 Ti + — + 32 GB RAM (windows)

Memory: 16 GB VRAM + 32 GB system RAM

Runner: llama.cpp / Ollama (CUDA)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
0 models

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

No models match this use case + hardware combination. Try a different use case or check tradeoffs below.

Runs with tradeoffs
11 models

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

Gemma 4 E2B (Effective 2B)

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 13.2 GBHeadroom: 2.8 GB

• Tight VRAM fit — only 2.8 GB headroom left for context growth

ollama run gemma4:e2b

214

tok/s

Weights

2.13 GB

KV cache

1.00 GB

Activations

8.30 GB

Runtime

1.80 GB

Model details →Run-on benchmark page →

Gemma 4 E4B (Effective 4B)

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 14.5 GBHeadroom: 1.5 GB

• Tight VRAM fit — only 1.5 GB headroom left for context growth

ollama run gemma4:e4b

188

tok/s

Weights

2.42 GB

KV cache

2.00 GB

Activations

8.31 GB

Runtime

1.80 GB

Model details →Run-on benchmark page →

Gemma 3 4B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 14.5 GBHeadroom: 1.5 GB

• Tight VRAM fit — only 1.5 GB headroom left for context growth

ollama run gemma3:4b

188

tok/s

Weights

2.42 GB

KV cache

2.00 GB

Activations

8.31 GB

Runtime

1.80 GB

Model details →Run-on benchmark page →

Phi-3.5 Vision

4.2B

phi

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 14.8 GBHeadroom: 1.2 GB

• Tight VRAM fit — only 1.2 GB headroom left for context growth

179

tok/s

Weights

2.54 GB

KV cache

2.10 GB

Activations

8.32 GB

Runtime

1.80 GB

Model details →Run-on benchmark page →

Llama 3.2 11B Vision Instruct

11B

llama

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 12.2 GBHeadroom: 3.8 GB

• Tight VRAM fit — only 3.8 GB headroom left for context growth

ollama run llama3.2-vision:11b

tok/s

Weights

6.64 GB

KV cache

1.38 GB

Activations

2.38 GB

Runtime

1.80 GB

Model details →Run-on benchmark page →

Gemma 3 12B

12B

gemma

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 13.0 GBHeadroom: 3.0 GB

• Tight VRAM fit — only 3.0 GB headroom left for context growth

ollama run gemma3:12b

tok/s

Weights

7.25 GB

KV cache

1.50 GB

Activations

2.41 GB

Runtime

1.80 GB

Model details →Run-on benchmark page →

Pixtral 12B

12B

mistral

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 13.0 GBHeadroom: 3.0 GB

• Tight VRAM fit — only 3.0 GB headroom left for context growth

ollama run pixtral:12b

tok/s

Weights

7.25 GB

KV cache

1.50 GB

Activations

2.41 GB

Runtime

1.80 GB

Model details →Run-on benchmark page →

Gemma 4 26B MoE

26B

gemma

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 23.6 GBHeadroom: 11.6 GB

• Partial CPU offload: ~32% of layers run on CPU

ollama run gemma4:26b-moe

tok/s

Weights

15.70 GB

KV cache

3.25 GB

Activations

2.83 GB

Runtime

1.80 GB

Model details →Run-on benchmark page →

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: 10 new comfortable, 37 new tradeoff

• Gemma 3 1B
• Llama 3.2 1B Instruct
• DeepSeek R1 Distill Qwen 7B
• Llama 3.1 8B Instruct

Shop this upgrade↗

Upgrade to NVIDIA GeForce RTX 3090

~$899

24 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~? GB/s to ~? GB/s.

Unlocks: 20 new comfortable

• Gemma 3 1B
• Llama 3.2 1B Instruct
• Gemma 4 E2B (Effective 2B)
• Llama 3.2 3B Instruct

Shop this upgrade↗

Add a second NVIDIA GeForce RTX 5070 Ti

~$849

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: 34 new comfortable

• Gemma 3 1B
• Llama 3.2 1B Instruct
• Gemma 4 E2B (Effective 2B)
• Llama 3.2 3B Instruct

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.

Qwen 3 235B-A22B

235B

qwen

Commercial OK