SmolLM3-3B — 3.1B Parameter Dense LLM
Model Specifications
- Parameters
- 3.1B
- Architecture
- Dense Transformer
- Context Length
- 64K tokens
- Capabilities
- chat
- Release Date
- 2025-07-01
- Provider
- HuggingFace
- Family
- smollm
VRAM Requirements
| Quantization | BPW | VRAM | Quality |
|---|---|---|---|
| Q4_K_M | 4.89 | 2.4 GB | 94% |
| Q5_K_S | 5.57 | 2.6 GB | 96% |
| Q5_K_M | 5.7 | 2.7 GB | 96% |
| Q6_K | 6.56 | 3.0 GB | 97% |
| Q8_0 | 8.5 | 3.8 GB | 100% |
| FP16 | 16 | 6.7 GB | 100% |
Benchmark Scores
HumanEval30.5
MMLU-PRO10.7
MATH46.1
IFEval76.7
BBH10.9
GPQA35.7
MUSR2.8
How to Run SmolLM3-3B
Run SmolLM3-3B locally with Ollama (needs 2.4 GB VRAM at Q4_K_M):
ollama run smollm:3bCompatible GPUs (30)
GPUs that can run SmolLM3-3B at Q4_K_M quantization:
NVIDIA Quadro 5000(3GB, 120 GB/s)NVIDIA Quadro 5000 SDI(3GB, 120 GB/s)NVIDIA Tesla C2050(3GB, 144 GB/s)NVIDIA Tesla M2050(3GB, 148 GB/s)NVIDIA Tesla S2050(3GB, 148 GB/s)NVIDIA GeForce GTX 670MX(3GB, 67 GB/s)AMD Radeon HD 7950(3GB, 240 GB/s)AMD Radeon HD 7950 Boost(3GB, 240 GB/s)AMD Radeon HD 7950 Monica BIOS 1(3GB, 240 GB/s)AMD Radeon HD 7950 Monica BIOS 2(3GB, 240 GB/s)AMD Radeon HD 7970(3GB, 264 GB/s)AMD Radeon HD 7970 GHz Edition(3GB, 288 GB/s)AMD Radeon HD 7970 X2(3GB, 264 GB/s)NVIDIA GeForce GTX 770M(3GB, 96 GB/s)NVIDIA GeForce GTX 780(3GB, 288 GB/s)