 |
VOOZH | about |
Intel
Operating mode
Use this to bias workload recommendations toward responsiveness, background autonomy, lighter serving, or multi-GPU scale-out.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
The Arc Pro A60 12GB is a workstation GPU based on the first-generation Alchemist architecture, offering professional-certified drivers for CAD and visualization workloads alongside AI inference capability. Its 12 GB of GDDR6 accommodates 7B models at FP16 and 13B at Q4 quantization on-GPU. As an Alchemist-generation card, its XMX engines are less capable than Battlemage, but workstation driver certification provides better stability than the consumer A-series for professional use cases.
Beyond LLMs
What AI tasks this GPU can handle — from text generation to image and video creation.
| Capability | Status | Representative Model | Detail |
|---|---|---|---|
| LLM Chat (7B) | Runs natively | Llama 3.1 8B Q4 | — |
| LLM Coding (30B) | Won’t fit | Qwen 3 30B Q4 | — |
| LLM Large (70B) | Won’t fit | Llama 3.1 70B Q4 | — |
| Image Gen (SDXL) | Runs natively | SDXL 1.0 FP16 | ~~26.8s per image |
| Image Gen (Flux) | Won't fit | Flux.1 Dev FP16 | ~~2m 1s per image |
| Image Gen (SD 3.5) | Won't fit | SD 3.5 Large FP16 | ~~2m 27s per image |
| Video Short (25f) | Runs with offload | LTX Video 2B | ~~23.2s/frame |
| Video Long (100f) | Won't fit | Wan Video 14B | ~~1m 9s/frame |
Architecture
Alchemist is Intel's first discrete GPU architecture under the Arc brand, using Xe-HPG cores manufactured on TSMC's N6 process. It features XMX (Xe Matrix Extensions) engines for AI acceleration.
AI Relevance
XMX engines provide some AI inference acceleration via oneAPI/SYCL. However, the software ecosystem for LLM inference on Intel Arc is still developing, with limited runtime support compared to CUDA.
Buying advice
Usable for local AI with limits
Can run 10 of 50 top models, mostly smaller ones. Larger models need heavy quantization or won't fit.
12.0 GB
VRAM
$499
MSRP
$42/GB
Cost per GB VRAM
Best models for this GPU
What will limit you first
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Runtime ecosystem is narrower than CUDA
Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.
Best upgrade itinerary
Prefer CUDA if you want the path of least resistance
If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.
Unlocks 1 additional models that do not fit on the current setup.
Want more headroom? MacBook Pro M3 Pro 18GB (18.0 GB unified memory) is the next step up.
Chat
SThis model is a direct match for chat. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
Coding
SThis model is a direct match for coding. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
Agentic Coding
AThis model is still usable for agentic-coding, but it is not the most specialized pick. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
Reasoning
SThis model is a direct match for reasoning. It belongs to a current frontier family for local AI. It fits natively with comfortable headroom. Known channels: huggingface, ollama, lm-studio.
RAG
AThis model is still usable for rag, but it is not the most specialized pick. It sits in the middle of the current model mix. It fits natively with comfortable headroom. Known channels: huggingface, ollama.
Just out of reach
High-quality models that need a bit more memory
Image & Video Generation
24 of 52 models can generate images or video on your Intel Arc Pro A60 12GB
| Model | Max Resolution | Gen Time | Grade |
|---|---|---|---|
| SD TurboImage | 512×512 | ~3.3s | S |
| Stable Diffusion 1.5Image | 512×768 | ~6.7s | S |
| Realistic Vision v5.1Image | 512×768 | ~6.7s | S |
| DreamShaper 8Image | 512×768 | ~6.7s | S |
| LCM DreamShaper v7Image | 512×768 | ~2s | S |
| PixArt-SigmaImage | 256×256 | ~2m 1s | S |
| FramePack I2VVideo | 256×256 | ~49.2s/frame | S |
| SDXL TurboImage | 512×512 | ~3.3s | S |
| SDXL LightningImage | 1024×1024 | ~10s | S |
| Stable Diffusion XL 1.0Image | 1024×1024 | ~26.8s | S |
| Playground v2.5Image | 1024×1024 | ~40.2s | S |
| RealVisXL v5.0Image | 1024×1024 | ~30.1s | S |
| DreamShaper XLImage | 1024×1024 | ~30.1s | S |
| Juggernaut XL v9Image | 1024×1024 | ~30.1s | S |
| Animagine XL 3.1Image | 1024×1024 | ~30.1s | S |
| Pony Diffusion V6 XLImage | 1024×1024 | ~30.1s | S |
| Animagine XL 4.0Image | 1024×1024 | ~30.1s | S |
| Illustrious XLImage | 1024×1024 | ~30.1s | S |
| Wan Video 2.1 1.3BVideo | 256×256 | ~19.6s/frame | A |
| Stable Diffusion 3.5 MediumImage | 256×256 | ~46.9s | A |
| Flux.2 Klein 4BImage | 256×256 | ~18.1s | A |
| LTX Video 2BVideo | 256×256 | ~23.2s/frame | B |
| KolorsImage | 256×256 | ~53.6s | B |
| Stable CascadeImage | 1024×1024 | ~1m 7s | D |
| AuraFlow v0.3Image | 256×256 | ~2m 1s | F |
| Stable Diffusion 3.5 LargeImage | 256×256 | ~2m 27s | F |
| Stable Diffusion 3.5 Large TurboImage | 256×256 | ~26.8s | F |
| CogVideoX 2BVideo | 256×256 | ~23.2s/frame | F |
| HunyuanVideoVideo | 256×256 | ~49.2s/frame | F |
| ChromaImage | 256×256 | ~26.8s | F |
| Z-Image TurboImage | 256×256 | ~27.6s | F |
| Flux.1 DevImage | 256×256 | ~2m 1s | F |
| Flux.1 SchnellImage | 256×256 | ~23.4s | F |
| LTX Video 13BVideo | 256×256 | ~49.2s/frame | F |
| Flux.1 Kontext DevImage | 256×256 | ~2m 14s | F |
| AnimateDiff v1.5.3Video | 512×768 | ~12.2s/frame | F |
| Cosmos Diffusion 7BVideo | 256×256 | ~38.4s/frame | F |
| CogVideoX 5BVideo | 256×256 | ~33.5s/frame | F |
| Wan2.2 TI2V 5BVideo | 256×256 | ~33.5s/frame | F |
| Flux.2 Klein 9BImage | 256×256 | ~13.4s | F |
| Flux.1 Fill DevImage | 256×256 | ~1m 54s | F |
| Mochi 1 PreviewVideo | 256×256 | ~44.3s/frame | F |
| HunyuanVideo 1.5Video | 256×256 | ~41.1s/frame | F |
| Helios 14BVideo | 256×256 | ~50.6s/frame | F |
| SkyReels V2 14BVideo | 256×256 | ~50.6s/frame | F |
| Wan Video 2.1 14BVideo | 256×256 | ~50.6s/frame | F |
| Wan Video 2.2 14BVideo | 256×256 | ~50.6s/frame | F |
| Qwen ImageImage | 256×256 | ~45.1s | F |
| Qwen Image EditImage | 256×256 | ~45.1s | F |
| Flux.2 DevImage | 256×256 | ~21m 7s | F |
| MAGI-1Video | 256×256 | ~1m 3s/frame | F |
| HunyuanImage 3.0Image | 256×256 | ~1m 19s | F |
Image models estimated at 1024×1024 (28 steps, FP16). Video models estimated at 768×512 (25 frames, 30 steps, FP16). Actual performance varies with runtime and system load.
Upgrade paths
See what you unlock with more powerful hardware
Upgrade options
Unlocks 1 additional models that do not fit on the current setup.
~$1,999 MSRP
Unlocks 37 additional models that do not fit on the current setup.
~$399 MSRP
Unlocks 73 additional models that do not fit on the current setup.
~$599 MSRP
Unlocks 118 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 338%.
~$8,000 MSRP
Compare with similar
