Autor: Jakub Rusinowski · Ostatnia aktualizacja: 10 lipca 2026
The smallest production-quality LLMs. HuggingFace's SmolLM2 models are designed to run on microcontrollers, phones, and browsers via WebAssembly. Despite tiny size, they show surprising intelligence thanks to careful data curation with the Smoltalk dataset.
| SmolLM2 1.7B Instruct | Min 1 GB VRAM · Q4_K_M · 8,192 ctx · ollama run smollm2:1.7b |
| SmolLM2 360M Instruct | Min 1 GB VRAM · Q4_K_M · 8,192 ctx · ollama run smollm2:360m |
The cheapest GPU that runs SmolLM2 locally (min 1 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run smollm2:1.7b
Minimum VRAM: 1 GB. For best results use Q4_K_M quantization.
SmolLM2 needs about 1 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: SmolLM2 1.7B Instruct (1 GB, Q4_K_M); SmolLM2 360M Instruct (1 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — SmolLM2 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 SmolLM2 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 smollm2:1.7b. This downloads SmolLM2 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.