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

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

Memory: 24 GB VRAM + 32 GB system RAM
Runner: llama.cpp (Vulkan)

Runs comfortably
161 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: Q8_0Context: 8,192VRAM: 13.9 GBHeadroom: 10.1 GB
ollama run hermes3:8b
24
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
1.00 GB
#2Gemma 2 9B Instruct
9B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 15.8 GBHeadroom: 8.2 GB
ollama run gemma2:9b
21
tok/s
Estimated
Weights
9.80 GB
KV cache
4.50 GB
Activations
0.50 GB
Runtime
1.00 GB
#3Hermes 3 Llama 3.2 3B
3B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.4 GBHeadroom: 19.6 GB
113
tok/s
Estimated
Weights
1.80 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.00 GB
#4Dolphin 3.0 Llama 3.2 3B
3B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.4 GBHeadroom: 19.6 GB
113
tok/s
Estimated
Weights
1.80 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.00 GB
#5Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.2 GBHeadroom: 20.8 GB
170
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
1.00 GB
#6Gemma 4 E2B (Effective 2B)
2B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 4.3 GBHeadroom: 19.7 GB
ollama run gemma4:e2b
97
tok/s
Estimated
Weights
2.20 GB
KV cache
1.00 GB
Activations
0.12 GB
Runtime
1.00 GB
#7Dolphin 3.0 8B
8B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.3 GBHeadroom: 13.7 GB
ollama run dolphin3:8b
42
tok/s
Estimated
Weights
5.00 GB
KV cache
4.00 GB
Activations
0.26 GB
Runtime
1.00 GB
#8Qwen 3 1.7B
1.7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.8 GBHeadroom: 21.2 GB
200
tok/s
Estimated
Weights
0.90 GB
KV cache
0.85 GB
Activations
0.05 GB
Runtime
1.00 GB
#9DeepSeek V2 Lite Chat
15.7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 6.1 GB
142
tok/s
Estimated
Weights
8.60 GB
KV cache
7.85 GB
Activations
0.44 GB
Runtime
1.00 GB
#10Kumru 2B
2.4B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.8 GBHeadroom: 20.2 GB
ollama run alibayram/kumru:latest
142
tok/s
Estimated
Weights
1.50 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
1.00 GB
#11Qwen 3.5 2B Turkish SFT
2B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.2 GBHeadroom: 20.8 GB
170
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
1.00 GB
#12Kanarya 2B
2B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.4 GBHeadroom: 21.6 GB
170
tok/s
Estimated
Weights
1.10 GB
KV cache
0.25 GB
Activations
0.06 GB
Runtime
1.00 GB

Runs with tradeoffs
56 models

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

Jamba 1.5 Mini
52B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 39.0 GBHeadroom: 4.2 GB
  • • Partial CPU offload: ~38% of layers run on CPU
28
tok/s
Estimated
Weights
30.00 GB
KV cache
6.50 GB
Activations
1.50 GB
Runtime
1.00 GB
Gemma 3 12B
12B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 20.7 GBHeadroom: 3.3 GB
  • • Tight VRAM fit — only 3.3 GB headroom left for context growth
ollama run gemma3:12b
16
tok/s
Estimated
Weights
13.00 GB
KV cache
6.00 GB
Activations
0.66 GB
Runtime
1.00 GB
Gemma 4 26B MoE
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 21.1 GBHeadroom: 2.9 GB
  • • Tight VRAM fit — only 2.9 GB headroom left for context growth
ollama run gemma4:26b-moe
13
tok/s
Estimated
Weights
16.00 GB
KV cache
3.25 GB
Activations
0.80 GB
Runtime
1.00 GB
Gemma 4 26B-A4B
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 21.1 GBHeadroom: 2.9 GB
  • • Tight VRAM fit — only 2.9 GB headroom left for context growth
ollama run gemma4:26b-a4b-it-q4_K_M
13
tok/s
Estimated
Weights
16.00 GB
KV cache
3.25 GB
Activations
0.80 GB
Runtime
1.00 GB
Gemma 3 27B
27B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 21.2 GBHeadroom: 2.8 GB
  • • Tight VRAM fit — only 2.8 GB headroom left for context growth
ollama run gemma3:27b
13
tok/s
Estimated
Weights
16.00 GB
KV cache
3.38 GB
Activations
0.80 GB
Runtime
1.00 GB
MedGemma 27B
27B
gemma
Quant: Q4_K_MContext: 2,048VRAM: 21.2 GBHeadroom: 2.8 GB
  • • Tight VRAM fit — only 2.8 GB headroom left for context growth
13
tok/s
Estimated
Weights
16.00 GB
KV cache
3.38 GB
Activations
0.80 GB
Runtime
1.00 GB
GPT-OSS Swallow 20B RL v0.1
20B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 22.6 GBHeadroom: 1.4 GB
  • • Tight VRAM fit — only 1.4 GB headroom left for context growth
17
tok/s
Estimated
Weights
11.00 GB
KV cache
10.00 GB
Activations
0.56 GB
Runtime
1.00 GB
Mistral Nemo 12B Instruct
12B
mistral
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 20.7 GBHeadroom: 3.3 GB
  • • Tight VRAM fit — only 3.3 GB headroom left for context growth
ollama run mistral-nemo:12b
16
tok/s
Estimated
Weights
13.00 GB
KV cache
6.00 GB
Activations
0.66 GB
Runtime
1.00 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: 23 new comfortable, 73 new tradeoff

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

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: 104 new comfortable

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

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: 76 new comfortable

  • • Qwen 3 0.6B
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen3.6 27B

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 (24 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 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 (24 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 (24 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 (24 GB) + 60% of system RAM (19 GB) combined.

—

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.