Arc Pro B70 32 GB for local AI
Which image and video models run on the Arc Pro B70 32 GB, which file to download for each, and how much VRAM they need.
VRAM32 GB
MemoryGDDR6
Bus256-bit
Bandwidth608 GB/s
ArchitectureBattlemage
Launched2026-03
Launch price$949
Runs well47 of 49
Specs: www.intel.com · launch: www.igorslab.de
01What runs on it
| Model | Verdict | Best file | Size | Needed |
|---|---|---|---|---|
| image models | ||||
| FLUX.1 [dev] | Runs well | 16-bit | 23.8 GB | 26.1 GB |
| FLUX.1 [schnell] | Runs well | 16-bit | 23.8 GB | 26.1 GB |
| FLUX.1 Kontext [dev] | Runs well | 16-bit | 23.8 GB | 26.4 GB |
| FLUX.1 Krea [dev] | Runs well | 16-bit | 23.8 GB | 26.1 GB |
| FLUX.1 Fill [dev] | Runs well | 16-bit | 23.8 GB | 26.4 GB |
| FLUX.2 [dev] | Runs | Q6_K | 27.4 GB | 30.7 GB |
| FLUX.2 [klein] 9B | Runs well | 16-bit | 18.2 GB | 20.5 GB |
| FLUX.2 [klein] 4B | Runs well | 16-bit | 7.8 GB | 9.6 GB |
| Krea 2 (Turbo) | Runs well | 16-bit | 26.3 GB | 28.9 GB |
| Qwen-Image | Runs well | Q8_0 | 21.8 GB | 24.6 GB |
| Qwen-Image-Edit (2511) | Runs well | Q8_0 | 21.8 GB | 24.8 GB |
| Qwen-Image 2.1 | Runs well | 16-bit | 14.2 GB | 16.5 GB |
| Z-Image Turbo | Runs well | 16-bit | 12.3 GB | 14.3 GB |
| Z-Image (base) | Runs well | 16-bit | 12.3 GB | 14.3 GB |
| Ideogram 4 | Runs well | Q8_0 | 10.1 GB | 22.6 GB |
| Boogu-Image (Turbo) | Runs well | 16-bit | 20.6 GB | 23.2 GB |
| ERNIE-Image (Turbo) | Runs well | 16-bit | 16.1 GB | 18.4 GB |
| HiDream-O1-Image | Runs well | 16-bit | 16.4 GB | 19.2 GB |
| Mage-Flow (Microsoft) | Runs well | 16-bit | 8.2 GB | 10.0 GB |
| Lumina Image 2.0 | Runs well | 16-bit | 5.2 GB | 7.0 GB |
| HiDream-I1 (Full) | Runs well | Q8_0 | 18.7 GB | 21.5 GB |
| HiDream-I1 (Dev) | Runs well | Q8_0 | 18.7 GB | 21.5 GB |
| Stable Diffusion 3.5 Large | Runs well | 16-bit | 16.5 GB | 18.8 GB |
| Stable Diffusion 3.5 Medium | Runs well | 16-bit | 5.1 GB | 6.9 GB |
| Chroma1-HD | Runs well | 16-bit | 17.8 GB | 20.1 GB |
| SDXL 1.0 | Runs well | 16-bit | 6.9 GB | 7.1 GB |
| Illustrious XL / Pony (SDXL anime) | Runs well | 16-bit | 6.9 GB | 7.1 GB |
| Stable Diffusion 1.5 | Runs well | 16-bit | 2.1 GB | 3.3 GB |
| HunyuanImage 2.1 | Runs well | Q8_0 | 19.8 GB | 23.1 GB |
| video models | ||||
| Wan 2.1 T2V 14B | Runs well | Q8_0 | 15.9 GB | 20.2 GB |
| Wan 2.1 T2V 1.3B | Runs well | 16-bit | 2.8 GB | 5.6 GB |
| Wan 2.1 I2V 14B 480P | Runs well | Q8_0 | 18.1 GB | 22.4 GB |
| Wan 2.1 I2V 14B 720P | Runs well | Q8_0 | 18.1 GB | 24.9 GB |
| Wan 2.1 VACE 14B | Runs well | Q8_0 | 18.7 GB | 23.5 GB |
| Wan 2.2 T2V A14B | Runs well | Q8_0 | 15.4 GB | 19.7 GB |
| Wan 2.2 I2V A14B | Runs well | Q8_0 | 15.4 GB | 19.7 GB |
| Wan 2.2 TI2V 5B | Runs well | 16-bit | 10.0 GB | 13.8 GB |
| Wan 2.2 Animate 14B | Runs well | Q8_0 | 18.7 GB | 24.0 GB |
| Wan Animate 2 (14B) | Runs well | Q8_0 | 18.1 GB | 23.4 GB |
| Wan 2.2 S2V 14B | Runs well | Q8_0 | 19.6 GB | 24.4 GB |
| SCAIL-2 (character animation) | Runs well | Q8_0 | 18.1 GB | 23.4 GB |
| HunyuanVideo (13B, original) | Runs well | 16-bit | 25.6 GB | 29.9 GB |
| LTX-Video 13B (0.9.8) | Runs well | Q8_0 | 14.0 GB | 18.3 GB |
| HunyuanVideo 1.5 | Runs well | 16-bit | 16.7 GB | 21.0 GB |
| LTX-2 (19B) | Runs well | Q8_0 | 20.4 GB | 25.2 GB |
| LTX-2.3 (22B) | Runs well | Q8_0 | 22.8 GB | 27.6 GB |
| LTX-2.5 (22B) | Runs well | Q8_0 | 23.6 GB | 28.4 GB |
| MiniMax H3 (33B) | Runs | Q5_K_M | 23.9 GB | 29.7 GB |
| MiniMax H3 Pruned | Runs well | Q8_0 | 21.6 GB | 27.4 GB |
Calculated from real file sizes plus working memory. How the numbers work.
02Good to know
Intel Arc GPUs run ComfyUI through PyTorch's native XPU support on Windows 11 and Linux. Memory works the same as on NVIDIA, so the fit verdicts apply. FP8 files save memory but give no speed-up, and some custom nodes are NVIDIA-only. This is a workstation card sold at normal retail, listed because of its large memory.
03Measured and reported results
No measured results yet. Send yours.