Autor: Jakub Rusinowski · Ostatnia aktualizacja: 6 września 2026
Model library → SmolLM3 → SmolLM3 3B
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 needs about 3 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 3.08 Billion |
| Context window | 131,072 |
| Architecture | Dense Transformer |
| Provider | Hugging Face |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 8 GB |
| Record updated | 2026-09-06 |
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 1.0 GB | 1.8 GB | ~242 tok/s (est.) | Fits comfortably |
| Q3_K_M | 1.3 GB | 2.1 GB | ~220 tok/s (est.) | Fits comfortably |
| Q4_K_M | 1.9 GB | 2.7 GB | ~190 tok/s (est.) | Fits comfortably |
| Q5_K_M | 2.2 GB | 3.0 GB | ~176 tok/s (est.) | Fits comfortably |
| Q6_K | 2.5 GB | 3.3 GB | ~163 tok/s (est.) | Fits comfortably |
| Q8_0 | 3.3 GB | 4.1 GB | ~140 tok/s (est.) | Fits comfortably |
| F16 | 6.2 GB | 7.0 GB | ~91 tok/s (est.) | Fits comfortably |
Want the memory numbers alone, at every quantization level and your own context length? Use the SmolLM3 3B VRAM calculator.
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs SmolLM3 3B is the Intel Arc B570 (10 GB).
Install Ollama, then run:
ollama run smollm3:3bWeights on Hugging Face: HuggingFaceTB/SmolLM3-3B.
Best for: research, fine tuning, edge devices, multilingual.
← All SmolLM3 models | VRAM calculator | Check your own hardware