Arc Pro A60
Local inference speed
llama.cpp decode speed (tok/s) - estimated
| Workload | tok/s |
|---|---|
| LLaMA 3 8B Q4 | 44.9 |
Estimated - Estimated from memory bandwidth (llama.cpp decode) · updated 2026-11-05
Stacks for the Arc Pro A60
Complete local setups that run on 12 GB
AI pair programming in your terminal with local models, fully private
A private AI assistant on Windows with document RAG - no CLI, no Docker, all desktop GUI
A private AI coding assistant in your editor
Prototype and deploy multi-agent RAG applications visually with local models
Unify multiple local and cloud models behind a single OpenAI-compatible API
Arc Pro A60Link to this section
The Arc Pro A60 is an Intel GPU built on the Xe-HPG architecture, released 2023-06-06. For running AI locally, the numbers that matter are its 12 GB of GDDR6 and 384 GB/s of memory bandwidth. VRAM decides which models fit at all; bandwidth sets how fast they generate text.
What you can run on 12 GBLink to this section
At Q4_K_M quantization (the usual local default), 12 GB holds models up to roughly 19B parameters, leaving headroom for context. On this card you can run, among others:
- Qwen2.5-14B-Instruct - 14.8B parameters
- Qwen2.5-Coder-14B-Instruct - 14.8B parameters
- Phi-4 - 14B parameters
- Qwen3 14B - 14B parameters
- Wan2.1 T2V 14B - 14B parameters
Larger models need a higher-VRAM card, a second GPU, or CPU offload (which is much slower). Check any specific model with the VRAM calculator, or see the full picture on what can I run.
Local LLM speed (LLaMA 3, llama.cpp)Link to this section
Single-stream token-generation throughput - estimated from memory bandwidth:
| Model (quant) | Speed on Arc Pro A60 |
|---|---|
| Llama 3 8B (Q4_K_M) | 44.9 tok/s |
| Llama 3 8B (F16) | ✗ won't fit |
| Llama 3 70B (Q4_K_M) | ✗ won't fit |
Because decode is memory-bandwidth bound, the 384 GB/s figure is the best single predictor of chat speed on this card. Estimates are calibrated against measured RTX-40-series cards and are typically within ~15%.
Memory and powerLink to this section
- VRAM: 12 GB GDDR6 (192-bit bus)
- Bandwidth: 384 GB/s
- TDP: 130 W - a 300 W+ power supply is recommended
- Process: 6 nm
- Interface: PCIe 4.0 x16
Quantization and contextLink to this section
Quantization trades a little quality for a lot of VRAM. On 12 GB you can fit roughly a 19B model at Q4_K_M, about a 10B model at the higher-quality Q8, or a smaller model at full FP16. Longer context windows also consume VRAM (the KV cache grows with context length), so leave a few GB of headroom if you plan to use large prompts or many concurrent requests. For most chat and coding use, Q4_K_M on this card is the sweet spot between speed, quality, and the 12 GB budget.
How it comparesLink to this section
Similar cards for local AI, by VRAM and 8B-Q4 speed:
| GPU | VRAM | Bandwidth | Llama 3 8B Q4 |
|---|---|---|---|
| Arc Pro A60 | 12 GB | 384 GB/s | 44.9 tok/s |
| AMD Radeon RX 7700 XT | 12 GB | 432 GB/s | 50.6 tok/s |
| Intel Arc B580 | 12 GB | 456 GB/s | 53.4 tok/s |
| Radeon RX 7800M | 12 GB | 432 GB/s | 50.6 tok/s |
Bottom lineLink to this section
The Arc Pro A60 is best for budget-llm, image-gen. 12 GB is the practical entry point for serious local LLMs (7B-13B at Q4). If you need more, compare with AMD Radeon RX 7700 XT and Intel Arc B580.
SourcesLink to this section
- Specifications: RightNow GPU Database (TechPowerUp data)
- Benchmarks: GPU-Benchmarks-on-LLM-Inference (basis for the bandwidth estimate)
Specs and benchmarks last checked 2026-06-08. Verify current pricing before buying.
Frequently asked
Quick answers to common questions
How much VRAM does the Arc Pro A60 have?
The Arc Pro A60 has 12 GB of VRAM with 384 GB/s memory bandwidth.
What local AI models can run on the Arc Pro A60?
The Arc Pro A60 with 12 GB VRAM can run many models depending on quantization. Models up to ~18B params may fit at Q4_K_M. Use our VRAM calculator to check specific models.
Is the Arc Pro A60 good for local AI inference?
Arc Pro A60 is best for budget-llm, image-gen. Check our hardware directory for alternatives with more VRAM.
Where can I buy the Arc Pro A60?
Check our buy links above for the best current prices on Amazon, Newegg, and B&H. Prices vary by retailer and availability.
How does the Arc Pro A60 compare to other GPUs?
Arc Pro A60 has 12 GB VRAM and 384 GB/s bandwidth. It works best with smaller quantized models. Browse our hardware directory for side-by-side comparisons.
What power supply do I need for the Arc Pro A60?
The Arc Pro A60 has a TDP of 130W. A standard quality PSU of 650W+ should suffice. Always check the manufacturer's recommendations for your specific build.
Nearby options
Similar hardware and models that fit