HuggingFace
SmolLM2 135M
Tiny 135M model. Default LLM - guaranteed to run on any iPhone. Only 145MB download. Perfect for quick experiments.
0.135B parameterssmollmapache-2.08K context0.3GB - 0.5GB VRAM
Check Your Hardware
See which quantizations of SmolLM2 135M your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| Q8_0 | 8 | 0.14 GB | 0.3 GB | 0.5 GB | 98% |
| FP16 | 16 | 0.27 GB | 0.5 GB | 0.8 GB | 100% |
See It In Action
Real model outputs generated via RunThisModel.com — watch responses stream in real time.
Llama 3.3 70B responding...
Outputs generated by real AI models via RunThisModel.com. Generation speed shown is from cloud inference. Local speeds vary by hardware — check your device.
Frequently Asked Questions
How much VRAM do I need to run SmolLM2 135M?
SmolLM2 135M requires 0.3GB VRAM minimum with Q8_0 quantization. For full precision, you need 0.5GB VRAM.
What is the best quantization for SmolLM2 135M?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.