Qwen 3.7 — Alibaba Cloud 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Qwen 3.7 shipped as API-only Max and Plus tiers in May and June 2026. Alibaba skipped the generation for open weights and went straight to Qwen 3.8, so nothing in this family is locally runnable.
变体
Qwen 3.7 最小的变体在 Q4_K_M 下约需 22 GB 显存——量化权重加框架开销，不含 KV 缓存。
| 模型 | Q4 下显存 | 显存 | 上下文 | 运行 |
|---|---|---|---|---|
| Qwen 3.7 35B-A3B 35B (3B active) | ~21.9 GB | 262,144 | ollama run qwen3-7 |
显存为 Q4_K_M 下的量化权重加开销，与 GPU 与显存检测器使用同一引擎计算。
如何在本地运行 Qwen 3.7
安装 Ollama，然后拉取标签。
ollama run qwen3-7在上方选择一个尺寸，查看它自己的显存、速度估算和安装命令。
许可证
Commercial use permitted. No usage restrictions beyond attribution.
适用于: Qwen 3.7 35B-A3B推荐 GPU
目录中能在本地运行 Qwen 3.7（至少 22 GB 显存）的最便宜 GPU 是 NVIDIA GeForce RTX 5090 (32 GB).
Qwen 3.7 — 常见问题
How much VRAM does Qwen 3.7 need?
Qwen 3.7 needs about 22 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Qwen 3.7 35B-A3B (22 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Qwen 3.7 on an RTX 4090 (24 GB)?
Yes — Qwen 3.7 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Qwen 3.7?
Q4_K_M is the best balance of quality and VRAM for Qwen 3.7 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Qwen 3.7 with Ollama?
Qwen 3.7 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.