What can Intel Arc Pro B60 24GB run locally?

120 models fit comfortably on Intel Arc Pro B60 24GB with 32 GB system RAM. 56 more run with tradeoffs. Top pick: DeepSeek V3 Lite (16B MoE).

What's the recommended runner for this hardware?

llama.cpp (Vulkan). This is the runner that gives best tokens-per-second on Intel Arc Pro B60 24GB based on windows support and the GPU backend.

What can Intel Arc Pro B60 24GB run for reasoning?

Build: Intel Arc Pro B60 24GB + — + 32 GB RAM (windows)

Memory: 24 GB VRAM + 32 GB system RAM

Runner: llama.cpp (Vulkan)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
120 models

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

#1DeepSeek V3 Lite (16B MoE)

16B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 19.0 GBHeadroom: 5.0 GB

142

tok/s

Estimated

Weights

9.50 GB

KV cache

8.00 GB

Activations

0.48 GB

Runtime

1.00 GB

Model details →

#2Llama 3.1 Nemotron Nano 8B

llama

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 13.8 GB

tok/s

Estimated

Weights

4.90 GB

KV cache

4.00 GB

Activations

0.25 GB

Runtime

1.00 GB

Model details →

#3RefinedNeuro RN TR R1

llama

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 13.8 GB

ollama run RefinedNeuro/RN_TR_R1:latest

tok/s

Estimated

Weights

4.90 GB

KV cache

4.00 GB

Activations

0.25 GB

Runtime

1.00 GB

Model details →

#4DeepSeek R1 Distill Llama 8B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 14.1 GB

tok/s

Estimated

Weights

4.70 GB

KV cache

4.00 GB

Activations

0.24 GB

Runtime

1.00 GB

Model details →

#5NVIDIA Nemotron Nano 9B v2 Japanese

other

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 10.8 GBHeadroom: 13.2 GB

tok/s

Estimated

Weights

5.00 GB

KV cache

4.50 GB

Activations

0.26 GB

Runtime

1.00 GB

Model details →

#6DeepSeek R1 Distill Qwen 7B

deepseek

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 13.0 GBHeadroom: 11.0 GB

ollama run deepseek-r1:7b

tok/s

Estimated

Weights

8.10 GB

KV cache

3.50 GB

Activations

0.41 GB

Runtime

1.00 GB

Model details →

#7Phi-4 Reasoning 14B

14B

phi

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 16.8 GBHeadroom: 7.2 GB

ollama run phi4-reasoning:14b

tok/s

Estimated

Weights

8.40 GB

KV cache

7.00 GB

Activations

0.43 GB

Runtime

1.00 GB

Model details →

#8DeepSeek R1 Distill Qwen 14B

14B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 16.8 GBHeadroom: 7.2 GB

ollama run deepseek-r1:14b

tok/s

Estimated

Weights

8.40 GB

KV cache

7.00 GB

Activations

0.43 GB

Runtime

1.00 GB

Model details →

#9DeepSeek R1 Distill Mistral 24B

24B

deepseek

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 18.7 GBHeadroom: 5.3 GB

tok/s

Estimated

Weights

14.00 GB

KV cache

3.00 GB

Activations

0.70 GB

Runtime

1.00 GB

Model details →

#10InternLM 2.5 7B Chat

internlm

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.1 GBHeadroom: 14.9 GB

tok/s

Estimated

Weights

4.40 GB

KV cache

3.50 GB

Activations

0.23 GB

Runtime

1.00 GB

Model details →

#11Qwen 2.5 Math 7B

qwen

Commercial OK

Quant: Q4_K_MContext: 4,096VRAM: 7.4 GBHeadroom: 16.6 GB

tok/s

Estimated

Weights

4.40 GB

KV cache

1.75 GB

Activations

0.22 GB

Runtime

1.00 GB

Model details →

#12Qwen 3 7B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.1 GBHeadroom: 14.9 GB

tok/s

Estimated

Weights

4.40 GB

KV cache

3.50 GB

Activations

0.23 GB

Runtime

1.00 GB

Model details →

Runs with tradeoffs
56 models

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

Omni 31B Turkish Reasoning

31B

other

Quant: Q4_K_MContext: 2,048VRAM: 22.8 GBHeadroom: 1.2 GB

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

tok/s

Estimated

Weights

17.10 GB

KV cache

3.88 GB

Activations

0.86 GB

Runtime

1.00 GB

Model details →

DeepSeek R1 Distill Qwen 32B

32B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 6.2 GB

• Partial CPU offload: ~35% of layers run on CPU

ollama run deepseek-r1:32b

tok/s

Estimated

Weights

19.00 GB

KV cache

16.00 GB

Activations

0.96 GB

Runtime

1.00 GB

Model details →

QwQ 32B Preview

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 6.2 GB

• Partial CPU offload: ~35% of layers run on CPU

ollama run qwq:32b

tok/s

Estimated

Weights

19.00 GB

KV cache

16.00 GB

Activations

0.96 GB

Runtime

1.00 GB

Model details →

EXAONE 4.0.1 32B

32B

exaone

Quant: Q4_K_MContext: 2,048VRAM: 23.5 GBHeadroom: 0.5 GB

• Tight VRAM fit — only 0.5 GB headroom left for context growth

tok/s

Estimated

Weights

17.60 GB

KV cache

4.00 GB

Activations

0.88 GB

Runtime

1.00 GB

Model details →

Qwen3 Swallow 32B RL v0.2

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 23.5 GBHeadroom: 0.5 GB

• Tight VRAM fit — only 0.5 GB headroom left for context growth

tok/s

Estimated

Weights

17.60 GB

KV cache

4.00 GB

Activations

0.88 GB

Runtime

1.00 GB

Model details →

DeepSeek R1 Distill Qwen 3 32B

32B

deepseek

Commercial OK

Quant: AWQ-INT4Context: 8,192VRAM: 37.0 GBHeadroom: 6.2 GB

• Partial CPU offload: ~35% of layers run on CPU

tok/s

Estimated

Weights

19.00 GB

KV cache

16.00 GB

Activations

0.96 GB

Runtime

1.00 GB

Model details →

Sarvam M

24B

mistral

Commercial OK

Quant: Q4_K_MContext: 4,096VRAM: 20.9 GBHeadroom: 3.1 GB

• Tight VRAM fit — only 3.1 GB headroom left for context growth

tok/s

Estimated

Weights

13.20 GB

KV cache

6.00 GB

Activations

0.66 GB

Runtime

1.00 GB

Model details →

Magistral 32B

32B

mistral

Quant: AWQ-INT4Context: 8,192VRAM: 37.0 GBHeadroom: 6.2 GB

• Partial CPU offload: ~35% of layers run on CPU

tok/s

Estimated

Weights

19.00 GB

KV cache

16.00 GB

Activations

0.96 GB

Runtime

1.00 GB

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, 73 new tradeoff

• Qwen 3 0.6B
• Llama 3.2 3B Instruct
• Qwen 3 1.7B
• Gemma 3 270M

Shop this upgrade↗

Upgrade to Intel Gaudi 2

see current pricing

96 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~456 GB/s to ~2450 GB/s.

Unlocks: 145 new comfortable

• Qwen 3 0.6B
• Llama 4 Scout
• Qwen 3 30B-A3B
• Qwen 2.5 Coder 32B Instruct

Shop this upgrade↗

Add a second Intel Arc Pro B60 24GB

see current pricing

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: 117 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