Supported Models
Find the right model for your workload. Compare hardware support across text, vision, reranking, and generation, then open a deployment guide to get started.
✓ Supported
× Not supported
— Not documented
Language models for chat, reasoning, and text generation.
| Model / family | Ascend NPU | Cambricon MLU | Hygon DCU | Deployment guide |
|---|---|---|---|---|
| DeepSeek-V3 / R1 / V3.1 | ❌ | ✅ | ❌ | Not yet available |
| DeepSeek-V3.2 | ✅ | ✅ | ❌ | Not yet available |
| DeepSeek-V4 | ✅ | ✅ | — | Guide ↗ |
| Qwen2 / Qwen2.5 / QwQ | ❌ | ✅ | ✅ | Not yet available |
| Qwen3 | ✅ | ✅ | ✅ | Not yet available |
| Qwen3 MoE | ✅ | ✅ | ✅ | Not yet available |
| Qwen3.5 | ✅ | ✅ | — | Guide ↗ |
| GLM-5 | ✅ | ✅ | ❌ | Guide ↗ |
| GLM-5.1 / GLM-5.2 / GLM-5.3 | ✅ | ✅ | — | Guide ↗ |
| GLM-5.3-Flash | ✅ | — | — | Preview guide ↗ |
| MiniMax-M2.7 | ✅ | — | — | Preview guide ↗ |
Vision-language models for understanding images and text.
| Model / family | Ascend NPU | Cambricon MLU | Hygon DCU | Deployment guide |
|---|---|---|---|---|
| Qwen2.5-VL | ❌ | ✅ | ✅ | Not yet available |
| Qwen3-VL (dense) | ✅ | ✅ | ✅ | Not yet available |
| Qwen3-VL MoE | ❌ | ✅ | ✅ | Not yet available |
| GLM-5.3-Flash-VL | ✅ | — | — | Preview guide ↗ |
Rerank
Section titled “Rerank”Models for scoring and reordering retrieved documents.
| Model / family | Ascend NPU | Cambricon MLU | Hygon DCU | Deployment guide |
|---|---|---|---|---|
| Qwen3-Reranker | ✅ | ❌ | ❌ | Not yet available |
Diffusion models for image and video generation.
No matching models
Try another name, or reset the task and hardware filters.