New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Intel Arc Pro B60
Runs downloadable LLMs up to ~32.5B at Q4, ~59-73.3 tok/s on an 8B model.
What you can run
At 8k context, FP16 KV. Full-speed tok/s holds up to "max ctx"; beyond it the context spills to system RAM (CPU/PCIe offload) and drops to the degraded figure.
| Model size | FP16 | Q8 | Q4 |
|---|---|---|---|
| 3B |
44.1-54.7 t/s ≤222k ctx · then ~3.9-4.8 (slow) |
88.2-109.4 t/s ≤268k ctx · then ~7.7-9.6 (slow) |
157.4-195.4 t/s ≤288k ctx · then ~13.8-17.1 (slow) |
| 7-8B |
16.5-20.5 t/s ≤35k ctx · then ~1.5-1.8 (slow) |
33.1-41 t/s ≤96k ctx · then ~2.9-3.6 (slow) |
59-73.3 t/s ≤123k ctx · then ~5.2-6.4 (slow) |
| 13B | won't run |
20.3-25.3 t/s ≤46k ctx · then ~1.8-2.2 (slow) |
36.3-45.1 t/s ≤81k ctx · then ~3.2-4 (slow) |
| 32B | won't run | won't run |
14.8-18.3 t/s ≤10k ctx · then ~1.3-1.6 (slow) |
| 70B | won't run | won't run | won't run |
| 120B | won't run | won't run | won't run |
| 400B | won't run | won't run | won't run |
Estimate: tok/s ≈ bandwidth ÷ (params × bytes/param) × efficiency (Intel). Cyan = fits ~22.1 GB usable. Beyond "ctx", KV spills to system RAM (CPU/PCIe offload) (rough degraded speed shown).
What else you need for a full build▶
Minimum supporting components for a desktop built around the Intel Arc Pro B60. Guidance — exact needs depend on your case, other parts and how much you offload to system RAM.
Run popular models on the Intel Arc Pro B60
Videos about the Intel Arc Pro B60
Should You Buy Intel ARC PRO B60 for Local AI? Llama?
8 Arc Pro B60 GPUs in one box. Battle Matrix lab build!
More hardware like the Intel Arc Pro B60
About the Intel Arc Pro B60
Intel Arc Pro B60 is a discrete GPU from Intel, 2025. For local genAI the numbers that matter are its 24 GB (how big a model + context fits) and 456 GB/s bandwidth (generation speed).
Frequently asked questions
What size LLM can the Intel Arc Pro B60 run?▶
With ~22.1 GB usable it runs up to ~32.5B at Q4 (~9.5B at FP16) at 8k context. Bigger spills into system RAM (CPU/PCIe offload) and slows sharply.
How many tokens/sec does the Intel Arc Pro B60 generate?▶
Generation is bandwidth-bound. At 456 GB/s an 8B model at Q4 runs ~59-73.3 tok/s (estimate).
Why does long context slow it down?▶
The KV cache for the context must also fit fast memory; once weights+KV exceed 22.1 GB it spills to system RAM (CPU/PCIe offload) and throughput collapses. Each row shows the max usable context.
What else do I need to run the Intel Arc Pro B60?▶
Besides the card: at least 24GB of system RAM (2× the 24GB VRAM is ideal for CPU offload), a free PCIe x16 slot, any modern multi-core CPU, and a ≥1TB NVMe SSD for model weights.