What can Intel Arc A770 16GB run locally?

57 models fit comfortably on Intel Arc A770 16GB with 32 GB system RAM. 69 more run with tradeoffs. Top pick: Gemma 3 1B.

What's the recommended runner for this hardware?

llama.cpp (Vulkan). This is the runner that gives best tokens-per-second on Intel Arc A770 16GB based on windows support and the GPU backend.

What can Intel Arc A770 16GB run?

Build: Intel Arc A770 16GB + — + 32 GB RAM (windows)

Memory: 16 GB VRAM + 32 GB system RAM

Runner: llama.cpp (Vulkan)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
57 models

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

#1Gemma 3 1B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.3 GBHeadroom: 5.7 GB

ollama run gemma3:1b

417

tok/s

Weights

0.60 GB

KV cache

0.50 GB

Activations

8.22 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#2Llama 3.2 1B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 5.2 GB

ollama run llama3.2:1b

237

tok/s

Weights

1.06 GB

KV cache

0.50 GB

Activations

8.25 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#3DeepSeek R1 Distill Qwen 7B

deepseek

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB

ollama run deepseek-r1:7b

tok/s

Weights

4.23 GB

KV cache

0.88 GB

Activations

2.26 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#4Qwen 3 8B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB

ollama run qwen3:8b

tok/s

Weights

4.83 GB

KV cache

1.00 GB

Activations

2.29 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#5Mistral 7B Instruct v0.3

mistral

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB

ollama run mistral:7b

tok/s

Weights

4.23 GB

KV cache

0.88 GB

Activations

2.26 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#6Hermes 3 Llama 3.1 8B

hermes

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB

ollama run hermes3:8b

tok/s

Weights

4.83 GB

KV cache

1.00 GB

Activations

2.29 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#7Llama 3.1 Nemotron Nano 8B

llama

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB

tok/s

Weights

4.83 GB

KV cache

1.00 GB

Activations

2.29 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#8CodeGemma 7B

gemma

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 8.4 GBHeadroom: 7.6 GB

ollama run codegemma:7b

tok/s

Weights

4.23 GB

KV cache

0.88 GB

Activations

2.26 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#9Gemma 2 9B Instruct

gemma

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 9.9 GBHeadroom: 6.1 GB

ollama run gemma2:9b

tok/s

Weights

5.43 GB

KV cache

1.13 GB

Activations

2.32 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#10Llama 3.2 11B Vision Instruct

11B

llama

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 11.4 GBHeadroom: 4.6 GB

ollama run llama3.2-vision:11b

tok/s

Weights

6.64 GB

KV cache

1.38 GB

Activations

2.38 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#11DeepSeek R1 Distill Llama 8B

deepseek

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 9.1 GBHeadroom: 6.9 GB

tok/s

Weights

4.83 GB

KV cache

1.00 GB

Activations

2.29 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

#12EXAONE 3.5 8B

7.8B

exaone

Quant: Q4_K_MContext: 2,048VRAM: 9.0 GBHeadroom: 7.0 GB

tok/s

Weights

4.71 GB

KV cache

0.97 GB

Activations

2.28 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

Runs with tradeoffs
69 models

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

Llama 3.1 8B Instruct

llama

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 15.3 GBHeadroom: 0.7 GB

• Tight VRAM fit — only 0.7 GB headroom left for context growth

ollama run llama3.1:8b

tok/s

Weights

4.83 GB

KV cache

1.07 GB

Activations

8.43 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

Qwen 3 30B-A3B

30B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 25.8 GBHeadroom: 9.4 GB

• Partial CPU offload: ~38% of layers run on CPU

ollama run qwen3:30b

tok/s

Weights

18.11 GB

KV cache

3.75 GB

Activations

2.95 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

Qwen 2.5 Coder 32B Instruct

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 3.6 GB

• Partial CPU offload: ~49% of layers run on CPU

ollama run qwen2.5-coder:32b

tok/s

Weights

19.32 GB

KV cache

2.15 GB

Activations

9.16 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

Qwen 3 32B

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 27.3 GBHeadroom: 7.9 GB

• Partial CPU offload: ~41% of layers run on CPU

ollama run qwen3:32b

tok/s

Weights

19.32 GB

KV cache

4.00 GB

Activations

3.01 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

Gemma 4 31B Dense

31B

gemma

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 26.6 GBHeadroom: 8.6 GB

• Partial CPU offload: ~40% of layers run on CPU

ollama run gemma4:31b

tok/s

Weights

18.72 GB

KV cache

3.88 GB

Activations

2.98 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

DeepSeek R1 Distill Qwen 32B

32B

deepseek

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 27.3 GBHeadroom: 7.9 GB

• Partial CPU offload: ~41% of layers run on CPU

ollama run deepseek-r1:32b

tok/s

Weights

19.32 GB

KV cache

4.00 GB

Activations

3.01 GB

Runtime

1.00 GB

Model details →Run-on benchmark page →

Gemma 4 26B MoE

26B

gemma

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 22.8 GBHeadroom: 12.4 GB

• Partial CPU offload: ~30% 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

1.00 GB

Model details →Run-on benchmark page →

Qwen 3 14B

14B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 13.7 GBHeadroom: 2.3 GB

• Tight VRAM fit — only 2.3 GB headroom left for context growth

ollama run qwen3:14b

tok/s

Weights

8.45 GB

KV cache

1.75 GB

Activations

2.47 GB

Runtime

1.00 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: 78 new tradeoff

• Llama 3.1 8B Instruct
• Qwen 3 30B-A3B
• Qwen 2.5 Coder 32B Instruct
• Llama 3.3 70B Instruct

Shop this upgrade↗

Add a second Intel Arc A770 16GB

~$269

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: 56 new comfortable

• Gemma 4 E2B (Effective 2B)
• Llama 3.2 3B Instruct
• Phi-3.5 Vision
• Phi-3.5 Mini 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.

DeepSeek V4 Pro (1.6T MoE)

1600B

deepseek

Commercial OK