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 A370M 4GB is Intel's entry-level Alchemist mobile GPU, found in affordable laptops and thin-and-light designs. Its 4 GB of GDDR6 severely constrains AI inference to small quantized models — it can handle 3B or 7B Q4 models only with some CPU offloading. As an entry point to Intel's oneAPI ecosystem on mobile, it is better suited for light AI workloads and experimentation than production inference. The Vulkan backend in llama.cpp provides a simpler setup path than the full oneAPI SYCL stack.
Beyond LLMs
What AI tasks this GPU can handle — from text generation to image and video creation.
| Capability | Status | Representative Model |
|---|---|---|
| LLM Chat (7B) | Won’t fit | 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) | Won't fit | SDXL 1.0 FP16 |
| Image Gen (Flux) | Won't fit | Flux.1 Dev FP16 |
| Image Gen (SD 3.5) | Won't fit | SD 3.5 Large FP16 |
| Video Short (25f) | Won't fit | LTX Video 2B |
| Video Long (100f) | Won't fit | Wan Video 14B |
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.
購入アドバイス
制限付きでローカルAIに使用可能
上位50モデル中2モデルを実行可能（主に小規模）。大規模モデルには強い量子化が必要か、適合しません。
4.0 GB
VRAM
このGPUに最適なモデル
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 93 additional models that do not fit on the current setup.
もっと余裕が欲しいですか？ RTX 2060 6GB (6.0 GB VRAM) が次のステップアップです。
Chat
AThis 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
BThis model is still usable for coding, 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, lm-studio.
Agentic Coding
FThis 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 is likely to require compromise or offload. Known channels: huggingface, ollama, lm-studio.
Reasoning
BThis model is a direct match for reasoning. It sits in the middle of the current model mix. 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, lm-studio.
BGE M3
Jina Embeddings v3
Qwen3-Coder 30B A3B InstructQwen 3.5 397B A17B
Devstral 2 123B Instruct
Kimi K2.5Kimi K2.6
DeepSeek V4 ProQwen 3.5 27BQwen 3.6 27BQwen 3.5 122B A10BQwen3-VL 30B A3B InstructQwen 3.6 35B A3BDeepSeek V4 FlashQwen 3.5 9BQwen 3.5 35B A3BMagistral Small 2507Devstral Small 2 24B InstructQwen 3 32BQwen 3 14BQwen 3 30B A3BMistral Small 4 119B
Command A 111BQwen 2.5 VL 72B
GPT-OSS 120B
Nemotron 3 Nano 30BQwen 3.5 4BQwen 3 8BQwen3-Coder-Next
Phi-4-reasoning-plus 14BDevstral Small 1.1
GLM-5.1Pixtral Large 124BGLM-5DeepSeek V3.2GPT-OSS 20BQwen 3 235B A22BQwen3-Coder 480B A35B InstructNemotron Cascade 2 30B A3BPhi-4 Mini Reasoning 4B
Gemma 4 31BLeanstral 119B A6BDeepSeek Coder V2 236BDeepSeek R1 671BDeepSeek V3.1 671BNemotron Nano 8BMinistral 3 14B
EXAONE 4.0 32BGemma 4 26B A4Bもう少しで届く
もう少しメモリがあれば動く高品質モデル
Image & Video Generation
1 of 52 models can generate images or video on your Intel Arc A370M 4GB
| Model | Max Resolution | Gen Time | Grade |
|---|---|---|---|
| SD TurboImage | 512×512 | ~7.9s | D |
| Stable Diffusion 1.5Image | 512×768 | ~15.9s | F |
| Realistic Vision v5.1Image | 512×768 | ~15.9s | F |
| DreamShaper 8Image | 512×768 | ~15.9s | F |
| LCM DreamShaper v7Image | 512×768 | ~4.8s | F |
| PixArt-SigmaImage | 256×256 | ~1m 4s | F |
| FramePack I2VVideo | 256×256 | ~1m 57s/frame | F |
| SDXL TurboImage | 256×256 | ~7.9s | F |
| SDXL LightningImage | 256×256 | ~23.8s | F |
| Stable Diffusion XL 1.0Image | 256×256 | ~1m 4s | F |
| Playground v2.5Image | 256×256 | ~1m 35s | F |
| RealVisXL v5.0Image | 256×256 | ~1m 12s | F |
| DreamShaper XLImage | 256×256 | ~1m 12s | F |
| Juggernaut XL v9Image | 256×256 | ~1m 12s | F |
| Animagine XL 3.1Image | 256×256 | ~1m 12s | F |
| Pony Diffusion V6 XLImage | 256×256 | ~1m 12s | F |
| Animagine XL 4.0Image | 256×256 | ~1m 12s | F |
| Illustrious XLImage | 256×256 | ~1m 12s | F |
| Wan Video 2.1 1.3BVideo | 256×256 | ~46.5s/frame | F |
| Stable Diffusion 3.5 MediumImage | 256×256 | ~1m 51s | F |
| Flux.2 Klein 4BImage | 256×256 | ~19.1s | F |
| LTX Video 2BVideo | 256×256 | ~55.2s/frame | F |
| KolorsImage | 256×256 | ~2m 7s | F |
| Stable CascadeImage | 256×256 | ~2m 39s | F |
| AuraFlow v0.3Image | 256×256 | ~4m 46s | F |
| Stable Diffusion 3.5 LargeImage | 256×256 | ~5m 50s | F |
| Stable Diffusion 3.5 Large TurboImage | 256×256 | ~1m 4s | F |
| CogVideoX 2BVideo | 256×256 | ~55.2s/frame | F |
| HunyuanVideoVideo | 256×256 | ~1m 57s/frame | F |
| ChromaImage | 256×256 | ~1m 4s | F |
| Z-Image TurboImage | 256×256 | ~1m 6s | F |
| Flux.1 DevImage | 256×256 | ~4m 46s | F |
| Flux.1 SchnellImage | 256×256 | ~55.6s | F |
| LTX Video 13BVideo | 256×256 | ~1m 57s/frame | F |
| Flux.1 Kontext DevImage | 256×256 | ~5m 18s | F |
| AnimateDiff v1.5.3Video | 512×512 | ~29s/frame | F |
| Cosmos Diffusion 7BVideo | 256×256 | ~1m 31s/frame | F |
| CogVideoX 5BVideo | 256×256 | ~1m 20s/frame | F |
| Wan2.2 TI2V 5BVideo | 256×256 | ~1m 20s/frame | F |
| Flux.2 Klein 9BImage | 256×256 | ~31.8s | F |
| Flux.1 Fill DevImage | 256×256 | ~4m 30s | F |
| Mochi 1 PreviewVideo | 256×256 | ~1m 45s/frame | F |
| HunyuanVideo 1.5Video | 256×256 | ~1m 38s/frame | F |
| Helios 14BVideo | 256×256 | ~2m 0s/frame | F |
| SkyReels V2 14BVideo | 256×256 | ~2m 0s/frame | F |
| Wan Video 2.1 14BVideo | 256×256 | ~2m 0s/frame | F |
| Wan Video 2.2 14BVideo | 256×256 | ~2m 0s/frame | F |
| Qwen ImageImage | 256×256 | ~1m 47s | F |
| Qwen Image EditImage | 256×256 | ~1m 47s | F |
| Flux.2 DevImage | 256×256 | ~50m 9s | F |
| MAGI-1Video | 256×256 | ~2m 29s/frame | F |
| HunyuanImage 3.0Image | 256×256 | ~3m 9s | 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
アップグレードオプション
RTX 2060 6GB次のステップUnlocks 93 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 51%.
〜$349 MSRP
Intel Arc A380 6GBIntelアップグレードUnlocks 93 additional models that do not fit on the current setup.
〜$139 MSRP
Intel Arc B570 10GBコスパ最良Unlocks 164 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 89%.
〜$219 MSRP
Unlocks 286 additional models that do not fit on the current setup.
Lifts average decode speed across fitting models by about 693%.
〜$8,000 MSRP
Intel Arc A370M 4GB (4 GB VRAM) can run these top models: BGE M3 (score: 82/100), Jina Embeddings v3 (score: 73/100), Qwen3-Coder 30B A3B Instruct (score: 0/100). See the full compatibility list above.
Intel Arc A370M 4GB has 4 GB of VRAM available for AI model inference. This determines which models and quantization levels you can run locally.
Yes, Intel Arc A370M 4GB is excellent for running LLMs locally with top compatibility scores above 80/100.
For coding on Intel Arc A370M 4GB, we recommend Qwen 2.5 Coder 1.5B. It achieves 21.0 tokens per second with 33K context window. This model is still usable for coding, 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, lm-studio.
There are 4 upgrade path(s) from Intel Arc A370M 4GB: RTX 2060 6GB, Intel Arc A380 6GB. Upgrading would unlock larger models and faster inference speeds.
Flux.1 Dev requires around 24 GB of usable memory at FP16. With 4 GB, Intel Arc A370M 4GB cannot run Flux natively. Consider quantized GGUF variants or the smaller Schnell model with aggressive offloading.
Intel Arc A370M 4GB (4 GB VRAM) can handle various AI generation tasks beyond LLMs. For image generation, Stable Diffusion 1.5 fits comfortably. For video, video generation is limited by available memory. Check the AI Capability Matrix above for detailed compatibility.
Intel Arc A370M 4GB has limited capability for AI image generation with only 4 GB of usable memory. Stick to SD 1.5 at lower resolutions. For a better experience, consider hardware with at least 8 GB of usable accelerator memory.
Qwen 3.5 27B requires at least 16 GB of usable memory at Q4. With 4 GB, Intel Arc A370M 4GB can run the 4B variant at Q4 (2.4 GB). Consider upgrading memory capacity for larger Qwen models.
With 4 GB on Intel Arc A370M 4GB, stick to Q4_K_M for the best quality-to-size ratio. Only use Q2-Q3 if you must fit a model that otherwise would not load.
On Intel Arc A370M 4GB, capacity is usually the first gate: if the model does not fit, bandwidth does not matter. But once a model fits, memory bandwidth is what largely determines tokens per second. In practice, you want enough memory to fit the model plus headroom, then as much bandwidth as your budget allows.
Intel Arc A370M 4GB 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 A370M 4GB can still be useful.
Compare with similar
