SOURCE-REVIEWED MODEL PROFILE
SmolLM2-135M-Instruct
A compact instruction-tuned language model from Hugging Face’s SmolLM2 family for lightweight text generation and on-device experiments.
Metadata reviewed 2026-10-24 · Original creator: HuggingFaceTB
What it does
- Small-model text chat
- Short summaries and rewriting
- Lightweight local experiments
Local fit
CPU / small GPU. Try word games and short scene prompts. The smallest variants have limited reasoning and factual reliability; keep instructions simple.
Configuration value; backend support and enough memory are required. Start with a smaller context on limited hardware.
Evidence and limits
Source reviewed; no local generation benchmark for this exact checkpoint.
Connect a supported local text/vision backend; not independently tested
License and source
Keep upstream notices and check the exact downloaded artifact and parent-model terms. The original creator remains credited.
Read the original model card ↗
Reviewed source revision: 12fd25f77366fa6b3b4b768ec3050bf629380bac