What can Intel Arc Pro B60 24GB run for agents?
Build: Intel Arc Pro B60 24GB + — + 32 GB RAM (windows)
Runs comfortably120 models
Ranked by fit for agents use case + predicted speed. Click a row for VRAM breakdown.
Quant: Q8_0Context: 8,192VRAM: 13.9 GBHeadroom: 10.1 GBollama run hermes3:8b24tok/sEstimated
ollama run hermes3:8bQuant: Q5_K_MContext: 8,192VRAM: 19.0 GBHeadroom: 5.0 GBollama run qwen2.5:14b21tok/sEstimated
ollama run qwen2.5:14bQuant: Q4_K_MContext: 2,048VRAM: 18.7 GBHeadroom: 5.3 GBollama run dolphin-mistral:24b14tok/sEstimated
ollama run dolphin-mistral:24bQuant: Q8_0Context: 8,192VRAM: 10.0 GBHeadroom: 14.0 GBollama run qwen2.5:7b28tok/sEstimated
ollama run qwen2.5:7bQuant: Q5_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 14.1 GBollama run mistral:7b43tok/sEstimated
ollama run mistral:7bQuant: Q4_K_MContext: 8,192VRAM: 10.2 GBHeadroom: 13.8 GB42tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 11.4 GBHeadroom: 12.6 GBollama run ornith:9b38tok/sEstimated
ollama run ornith:9bQuant: Q4_K_MContext: 8,192VRAM: 15.5 GBHeadroom: 8.5 GBollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M28tok/sEstimated
ollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_MQuant: Q4_K_MContext: 2,048VRAM: 18.7 GBHeadroom: 5.3 GBollama run mistral-small:24b14tok/sEstimated
ollama run mistral-small:24bQuant: FP16Context: 8,192VRAM: 19.0 GBHeadroom: 5.0 GBollama run llama3.1:8b13tok/sEstimated
ollama run llama3.1:8bQuant: Q4_K_MContext: 8,192VRAM: 10.3 GBHeadroom: 13.7 GBollama run dolphin3:8b42tok/sEstimated
ollama run dolphin3:8bQuant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 6.1 GB142tok/sEstimated
Runs with tradeoffs56 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q4_K_MContext: 2,048VRAM: 23.7 GBHeadroom: 0.3 GB- • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run qwen3:30b11tok/sEstimated
- • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run qwen3:30bQuant: Q4_K_MContext: 8,192VRAM: 36.0 GBHeadroom: 7.2 GB- • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen3-coder:30b11tok/sEstimated
- • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen3-coder:30bQuant: Q4_K_MContext: 8,192VRAM: 23.1 GBHeadroom: 0.9 GB- • Tight VRAM fit — only 0.9 GB headroom left for context growth
ollama run qwen2.5-coder:32b11tok/sEstimated
- • Tight VRAM fit — only 0.9 GB headroom left for context growth
ollama run qwen2.5-coder:32bQuant: Q4_K_MContext: 8,192VRAM: 37.0 GBHeadroom: 6.2 GB- • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen2.5:32b11tok/sEstimated
- • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen2.5:32bQuant: Q4_K_MContext: 2,048VRAM: 23.7 GBHeadroom: 0.3 GB- • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run nemotron3:nano11tok/sEstimated
- • Tight VRAM fit — only 0.3 GB headroom left for context growth
ollama run nemotron3:nanoQuant: Q4_K_MContext: 8,192VRAM: 36.0 GBHeadroom: 7.2 GB- • Partial CPU offload: ~33% of layers run on CPU
ollama run north-mini-code-1.011tok/sEstimated
- • Partial CPU offload: ~33% of layers run on CPU
ollama run north-mini-code-1.0Quant: Q4_K_MContext: 8,192VRAM: 36.5 GBHeadroom: 6.7 GB- • Partial CPU offload: ~34% of layers run on CPU
ollama run glm-4.7-flash11tok/sEstimated
- • Partial CPU offload: ~34% of layers run on CPU
ollama run glm-4.7-flashQuant: Q5_K_MContext: 8,192VRAM: 40.1 GBHeadroom: 3.1 GB- • Partial CPU offload: ~40% of layers run on CPU
ollama run qwen3:32b9tok/sEstimated
- • Partial CPU offload: ~40% of layers run on CPU
ollama run qwen3:32bWhat 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
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
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
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Won't runtop 5 popular models
Need more memory than you have. Shown for orientation.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (19 GB) combined.
How to read these numbers
Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.