SmolLM Models by Hugging Face TB
3 models2024
About
A series of small language models built on a meticulously curated high-quality trainin corpus.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
3 in view
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| SmolLM 135M | Use when the workload needs 135M parameters. | 2024-12 | 135M parameters | Current |
| SmolLM 360M | Use when the workload needs 360M parameters. | 2024-12 | 360M parameters | Current |
| SmolLM 1.7B | Use when the workload needs 1.7B parameters. | 2024-12 | 1.7B parameters | Current |
Release Timeline
1 release group2024-12
3 current
Specifications(3 models)
| Model | Released | Parameters |
|---|---|---|
| SmolLM 135M | 2024-12 | 135M |
| SmolLM 360M | 2024-12 | 360M |
| SmolLM 1.7B | 2024-12 | 1.7B |
Frequently Asked Questions
- What is SmolLM used for?
- A series of small language models built on a meticulously curated high-quality trainin corpus.
- How does SmolLM compare to Claude 3?
- SmolLM by Hugging Face TB is strongest where you need its listed use cases, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. SmolLM has 3 listed variants, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
- Which SmolLM model should I use?
- If price is the main constraint, use the pricing table first because SmolLM does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate SmolLM 135M.