SmolLM3 3B — 显存、速度与本地部署
作者: Jakub Rusinowski · 最后更新:
3.08B dense, pretrained on 11.2T tokens across web, code, math and reasoning data. Native English, French, Spanish, German, Italian and Portuguese with additional Arabic, Chinese and Russian training. Runs on effectively anything — 2.7 GB at Q4_K_M — and unlike most small models the entire training pipeline is reproducible.
SmolLM3 3B 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。在 Apple Silicon 上,这部分来自统一内存。
按量化级别的显存与速度
计算基准:NVIDIA RTX 4090 (24 GB)。仅含权重与开销:该模型架构未公开,因此未计入 KV 缓存。
| 量化 | 显存 | 显存 | 速度(估算) | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 1.8 GB | ~242 tok/s | 可运行 | |
| Q3_K_M 3.41 bpw | 2.1 GB | ~220 tok/s | 可运行 | |
| Q4_K_M 4.83 bpw | 2.7 GB | ~190 tok/s | 可运行 | |
| Q5_K_M 5.67 bpw | 3 GB | ~176 tok/s | 可运行 | |
| Q6_K 6.56 bpw | 3.3 GB | ~163 tok/s | 可运行 | |
| Q8_0 8.50 bpw | 4.1 GB | ~140 tok/s | 可运行 | |
| F16 16.00 bpw | 7 GB | ~91 tok/s | 可运行 |
黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型,详见 方法说明页. SmolLM3 3B 显存计算器 →
运行 SmolLM3 3B
目录中能运行 SmolLM3 3B 的最便宜 GPU 是 Intel Arc B570 (10 GB).
或在 Vast.ai 比较,低至 $0.35/小时 (typical low · varies)
作为亚马逊联盟成员,我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金,您无需额外付费。
如何运行 SmolLM3 3B
安装 Ollama,然后运行:
ollama run smollm3:3b规格
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- 参数量
- 3.08 Billion
- 上下文窗口
- 131,072
- 架构
- Dense Transformer
- 提供商
- Hugging Face
- 许可证
- Apache 2.0
- Practical deployment
- Edge device (phone, SBC)
- 规格量化
- Q4_K_M
- 系统内存
- 8 GB
- 记录更新于
- 2026-09-06
Commercial use permitted. No usage restrictions beyond attribution.
质量与使用场景
评分由模型作者或独立评测方发布——衡量质量而非吞吐量,并非我们实测。
我的 GPU 能运行 SmolLM3 3B 吗?
SmolLM3 3B — 常见问题
How much VRAM does SmolLM3 3B need?
About 3 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does SmolLM3 3B run on an RTX 4090 (24 GB)?
Yes. SmolLM3 3B needs about 3 GB at Q4_K_M, inside a 24 GB card, at an estimated 190 tokens/sec.
How do I run SmolLM3 3B locally?
Install Ollama and run `ollama run smollm3:3b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.