作者： Jakub Rusinowski · 最后更新： 2026年9月6日
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.
| Licence | What it permits | Applies to |
|---|---|---|
Apache-2.0 | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | SmolLM3 3B |
| SmolLM3 3B | Min 3 GB VRAM · Q4_K_M · 131,072 ctx · ollama run smollm3:3b |
The cheapest GPU that runs SmolLM3 locally (min 3 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run smollm3:3b
Minimum VRAM: 3 GB. For best results use Q4_K_M quantization.
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.
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.
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.
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.