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 B60 24GB is Intel's top Battlemage workstation GPU, offering 24 GB of GDDR6 in a certified professional package. This VRAM capacity opens up 13B model inference at FP16 and 30B+ models at Q4 quantization entirely on-GPU — a significant capability at its $599 price point. The workstation driver stack provides ISV certifications for professional applications, while oneAPI enables LLM inference via llama.cpp's SYCL backend. It targets the intersection of professional visualization and AI-augmented workstation workflows.
Beyond LLMs
What AI tasks this GPU can handle — from text generation to image and video creation.
| Capability | Status | Representative Model |
|---|---|---|
| LLM Chat (7B) | Runs natively | Llama 3.1 8B Q4 |
| LLM Coding (30B) | Runs natively | Qwen 3 30B Q4 |
| LLM Large (70B) | Won’t fit | Llama 3.1 70B Q4 |
| Image Gen (SDXL) | Runs natively | SDXL 1.0 FP16 |
| Image Gen (Flux) | Runs with offload | Flux.1 Dev FP16 |
| Image Gen (SD 3.5) | Runs natively | SD 3.5 Large FP16 |
| Video Short (25f) | Runs natively | LTX Video 2B |
| Video Long (100f) | Won't fit | Wan Video 14B |
Architecture
Battlemage is Intel's second-generation Arc GPU architecture (Xe2-HPG), built on TSMC N4. It delivers significant performance-per-watt improvements over Alchemist with enhanced XMX engines and improved driver maturity.
AI Relevance
Better driver stability and improved XMX throughput make Battlemage more viable for AI inference than Alchemist. The Arc B580 (12 GB) is an increasingly popular budget option for local LLM experimentation via SYCL/oneAPI backends in llama.cpp.
购买建议
本地 AI 的绝佳选择
能良好运行 50 个顶级模型中的 26 个 — 本地推理的全能之选。
24.0 GB
VRAM
$599
建议零售价
$25/GB
每 GB VRAM 成本
最适合此 GPU 的模型
What will limit you first
The raw memory story may look fine, but the software ecosystem is still a constraint here.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Unlocks 1 additional models that do not fit on the current setup.
想要更多余量？ MacBook Pro M4 Max 36GB (36.0 GB unified memory) 是下一步升级选择。
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 should run, but memory headroom will be limited. Known channels: huggingface, ollama, lm-studio.
Agentic Coding
SThis 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 should run, but memory headroom will be limited. Known channels: huggingface, 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 a direct match for rag. It sits in the middle of the current model mix. It fits natively with comfortable headroom. Known channels: huggingface, ollama.
Qwen3-Coder 30B A3B InstructQwen3-VL 30B A3B Instruct
GPT-OSS 20BQwen 3 14B
Phi-4-reasoning-plus 14BQwen 3 30B A3BQwen 3.5 9BQwen 3.5 27B
Magistral Small 2507Devstral Small 2 24B InstructQwen 3.6 27BQwen 3 8BDevstral Small 1.1
Nemotron Cascade 2 30B A3BQwen 3.5 4BNemotron 3 Nano 30B
Gemma 4 26B A4BMinistral 3 14BNemotron Nano 8BPhi-4 Mini Reasoning 4BQwen 3.5 35B A3BQwen 3 32B
Jina Embeddings v3
BGE M3Qwen 3.6 35B A3B
EXAONE 4.0 32BQwen 3.5 397B A17BDevstral 2 123B Instruct
Kimi K2.5Kimi K2.6
DeepSeek V4 ProQwen 3.5 122B A10BDeepSeek V4 FlashMistral Small 4 119B
Command A 111BQwen 2.5 VL 72BGPT-OSS 120BQwen3-Coder-Next
GLM-5.1Pixtral Large 124BGLM-5DeepSeek V3.2Qwen 3 235B A22BQwen3-Coder 480B A35B InstructGemma 4 31BLeanstral 119B A6BDeepSeek Coder V2 236BDeepSeek R1 671BDeepSeek V3.1 671B触手可及
高质量模型，只需稍多一点内存
Image & Video Generation
41 of 52 models can generate images or video on your Intel Arc Pro B60 24GB
| Model | Max Resolution | Gen Time | Grade |
|---|---|---|---|
| SD TurboImage | 512×512 | ~4.7s | S |
| Stable Diffusion 1.5Image | 512×768 | ~9.4s | S |
| Realistic Vision v5.1Image | 512×768 | ~9.4s | S |
| DreamShaper 8Image | 512×768 | ~9.4s | S |
| LCM DreamShaper v7Image | 512×768 | ~2.8s | S |
| PixArt-SigmaImage | 1024×1024 | ~37.6s | S |
| FramePack I2VVideo | 256×256 | ~1m 9s/frame | S |
| SDXL TurboImage | 512×512 | ~4.7s | S |
| SDXL LightningImage | 1024×1024 | ~14.1s | S |
| Stable Diffusion XL 1.0Image | 1024×1024 | ~37.6s | S |
| Playground v2.5Image | 1024×1024 | ~56.4s | S |
| RealVisXL v5.0Image | 1024×1024 | ~42.3s | S |
| DreamShaper XLImage | 1024×1024 | ~42.3s | S |
| Juggernaut XL v9Image | 1024×1024 | ~42.3s | S |
| Animagine XL 3.1Image | 1024×1024 | ~42.3s | S |
| Pony Diffusion V6 XLImage | 1024×1024 | ~42.3s | S |
| Animagine XL 4.0Image | 1024×1024 | ~42.3s | S |
| Illustrious XLImage | 1024×1024 | ~42.3s | S |
| Wan Video 2.1 1.3BVideo | 256×256 | ~27.5s/frame | S |
| Stable Diffusion 3.5 MediumImage | 1024×1024 | ~1m 6s | S |
| Flux.2 Klein 4BImage | 1024×1024 | ~11.3s | S |
| LTX Video 2BVideo | 768×512 | ~32.6s/frame | S |
| KolorsImage | 1024×1024 | ~1m 15s | S |
| Stable CascadeImage | 1024×1024 | ~1m 34s | S |
| AuraFlow v0.3Image | 1536×1536 | ~2m 49s | S |
| Stable Diffusion 3.5 LargeImage | 1024×1024 | ~3m 27s | S |
| Stable Diffusion 3.5 Large TurboImage | 1024×1024 | ~37.6s | S |
| CogVideoX 2BVideo | 720×480 | ~32.6s/frame | A |
| HunyuanVideoVideo | 256×256 | ~1m 9s/frame | A |
| ChromaImage | 256×256 | ~1m 9s | A |
| Z-Image TurboImage | 1536×1536 | ~38.8s | B |
| Flux.1 DevImage | 256×256 | ~2m 49s | B |
| Flux.1 SchnellImage | 256×256 | ~32.9s | B |
| LTX Video 13BVideo | 256×256 | ~1m 9s/frame | B |
| Flux.1 Kontext DevImage | 256×256 | ~3m 8s | B |
| AnimateDiff v1.5.3Video | 512×768 | ~17.1s/frame | B |
| Cosmos Diffusion 7BVideo | 256×256 | ~1m 44s/frame | B |
| CogVideoX 5BVideo | 256×256 | ~1m 39s/frame | B |
| Wan2.2 TI2V 5BVideo | 256×256 | ~1m 39s/frame | B |
| Flux.2 Klein 9BImage | 256×256 | ~34.5s | D |
| Flux.1 Fill DevImage | 256×256 | ~2m 40s | D |
| Mochi 1 PreviewVideo | 256×256 | ~1m 2s/frame | F |
| HunyuanVideo 1.5Video | 256×256 | ~57.7s/frame | F |
| Helios 14BVideo | 256×256 | ~1m 11s/frame | F |
| SkyReels V2 14BVideo | 256×256 | ~1m 11s/frame | F |
| Wan Video 2.1 14BVideo | 256×256 | ~1m 11s/frame | F |
| Wan Video 2.2 14BVideo | 256×256 | ~1m 11s/frame | F |
| Qwen ImageImage | 256×256 | ~1m 3s | F |
| Qwen Image EditImage | 256×256 | ~1m 3s | F |
| Flux.2 DevImage | 256×256 | ~29m 39s | F |
| MAGI-1Video | 256×256 | ~1m 28s/frame | F |
| HunyuanImage 3.0Image | 256×256 | ~1m 52s | 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
升级选项
Unlocks 1 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 15%.
~$2,499 MSRP
Unlocks 17 additional models that do not fit on the current setup.
~$1,099 MSRP
Gaudi 3 128GBIntel 升级Unlocks 32 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 196%.
~$15,000 MSRP
Unlocks 45 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 307%.
~$8,000 MSRP
Intel Arc Pro B60 24GB (24 GB VRAM) can run these top models: Qwen3-Coder 30B A3B Instruct (score: 94/100), Qwen3-VL 30B A3B Instruct (score: 93/100), GPT-OSS 20B (score: 93/100). See the full compatibility list above.
Intel Arc Pro B60 24GB has 24 GB of VRAM available for AI model inference. This determines which models and quantization levels you can run locally.
Yes, Intel Arc Pro B60 24GB is excellent for running LLMs locally with top compatibility scores above 80/100.
For coding on Intel Arc Pro B60 24GB, we recommend Devstral Small 2 24B Instruct. It achieves 18.1 tokens per second with 40K context window. This model is a direct match for coding. It belongs to a current frontier family for local AI. It should run, but memory headroom will be limited. Known channels: huggingface, ollama, lm-studio.
There are 4 upgrade path(s) from Intel Arc Pro B60 24GB: MacBook Pro M4 Max 36GB, Mac mini M4 64GB. Upgrading would unlock larger models and faster inference speeds.
Yes, Intel Arc Pro B60 24GB with 24 GB of usable memory can run Flux.1 Dev at FP16 natively. Flux is a 12B parameter diffusion transformer that produces high-quality images. You can also run the Schnell variant for faster generation.
Intel Arc Pro B60 24GB (24 GB VRAM) can handle various AI generation tasks beyond LLMs. For image generation, SDXL and Stable Diffusion 3.5 run well. Flux.1 Dev also runs natively for state-of-the-art image quality. For video, LTX Video 2.3 can generate short clips. Check the AI Capability Matrix above for detailed compatibility.
Intel Arc Pro B60 24GB is excellent for AI image generation. With 24 GB of usable memory, it runs all major diffusion models including Flux.1, SDXL, and Stable Diffusion 3.5 at full precision. You can generate high-resolution images quickly and even handle video generation models.
Yes, Intel Arc Pro B60 24GB with 24 GB of usable memory can run Qwen 3.5 27B at Q4_K_M (~16.5 GB) with ~7 GB headroom for context and runtime. Quality at Q4 is very close to full precision for most tasks. Run it with: ollama run qwen3.5:27b
With 24 GB on Intel Arc Pro B60 24GB, Q4_K_M is the sweet spot for 27B-35B models, Q6_K for 14B models, and Q8_0 for 8B-9B models. The general rule: use the highest quantization that fits with at least 2-3 GB headroom for KV cache and runtime.
Intel Arc Pro B60 24GB has enough memory for many local LLMs, but bandwidth still matters a lot for real speed. Once a model fits, a faster-memory GPU can feel significantly better than a slower setup with similar capacity.
Intel Arc Pro B60 24GB can be attractive on memory-per-dollar, but CUDA still has the broadest support across runtimes, kernels, guides, and community-tested local AI workflows. If your priority is the easiest setup and widest model compatibility, NVIDIA remains the safer choice. If your priority is value and you are comfortable with a narrower software stack, Intel Arc Pro B60 24GB can still be useful.
Compare with similar
