SmolLM3 — Hugging Face 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Hugging Face's fully-open 3B: weights, training data, recipe and 100+ intermediate checkpoints all published. Dual-mode — a deep-thinking path for hard problems and a fast path for everything else — with 128K context and six natively supported languages. The reference model for anyone fine-tuning at the small end, which makes it the natural companion to the datasets hub.
变体
SmolLM3 最小的变体在 Q4_K_M 下约需 3 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 |
|---|---|---|---|---|
| SmolLM3 3B → 3B | ~2.7 GB | 131,072 | ollama run smollm3:3b |
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 SmolLM3
安装 Ollama，然后拉取标签。
ollama run smollm3:3b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: SmolLM3 3B推荐 GPU
目录中能在本地运行 SmolLM3（至少 3 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
我的 GPU 能运行 SmolLM3 吗？
SmolLM3 — 常见问题
How much VRAM does SmolLM3 need?
SmolLM3 needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: SmolLM3 3B (3 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run SmolLM3 on an RTX 4090 (24 GB)?
Yes — SmolLM3 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 SmolLM3?
Q4_K_M is the best balance of quality and VRAM for SmolLM3 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 SmolLM3 with Ollama?
Install Ollama, then run: ollama run smollm3:3b. This downloads SmolLM3 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.