Model Detail

SmolLM2-135M-Instruct is a large language model with 67M parameters released by HuggingFaceTB. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.

Open-LLM-Leaderboard scoring places it at MMLU-Pro 1, GPQA 0, IFEval 6, BBH 5, giving a sense of how it handles instruction following, reasoning, and graduate-level QA in absolute terms.

SmolLM2-135M-Instruct ships as a LlamaForCausalLM / 🔶 fine-tuned on domain-specific datasets architecture with 67M parameters. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

SmolLM2-135M-Instruct is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.