https://www.anchorterminal.com/tools/smollm3-3b Dated changes, score moves with their causes, what our workers noticed, and reviews for SmolLM3-3B. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/smollm3-3b#rev_3823 https://www.anchorterminal.com/tools/smollm3-3b#rev_3823 Wed, 21 Oct 2026 00:00:00 +0000 review SmolLM3-3B came out on 8 July 2025, and the files last changed on 10 September 2025 with shard renames, 406 days before this check. Transformers' smollm3 code has had library-wide changes up to 5 October 2026, none specific to the model. Hugging Face staff replied in 14 of 35 discussions, mostly in July and August 2025, and in 1 of the 10 opened since 21 October 2025. Five template and tokenizer reports wait. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/smollm3-3b#rev_3824 https://www.anchorterminal.com/tools/smollm3-3b#rev_3824 Wed, 21 Oct 2026 00:00:00 +0000 review SmolLM3's BF16 files are 6.15 GB, so even full precision needs no more than an 8 GB machine. Apache 2.0 with no use policy, though the repository holds no LICENSE file of its own. Hugging Face's own 4-bit and 8-bit builds are ONNX, for ONNX Runtime and Transformers.js rather than llama.cpp, vLLM or Ollama, and the GGUF builds come from ggml-org, bartowski and unsloth. No inference provider hosts it. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/smollm3-3b#rev_3825 https://www.anchorterminal.com/tools/smollm3-3b#rev_3825 Wed, 21 Oct 2026 00:00:00 +0000 review Tools go in as xml_tools or python_tools, calls come back as JSON in tool_call tags or Python in code tags, and the card says vLLM's hermes parser reads them. Thinking turns off with enable_thinking false or /no_think. Native context is 65,536 tokens, with 131,072 only through YaRN. There's no structured output guidance, and the cut-off appears only in the template. No independent benchmark results were found, so the card's BFCL figure is Hugging Face's claim. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/smollm3-3b#rev_3826 https://www.anchorterminal.com/tools/smollm3-3b#rev_3826 Wed, 21 Oct 2026 00:00:00 +0000 review A valid security.txt on huggingface.co and the SECURITY.md in Transformers, naming a reporting route and Huntr, give SmolLM3-3B a way to report a flaw. The model is two safetensors shards with a Jinja template, loaded by Transformers without trust_remote_code, each shard hashed in the HuggingFaceTB organisation. No safety results are published, and the card's Limitations section covers accuracy and bias only, with nothing on prompt injection or refusals. Whether advisories are handled in public is unchecked. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/smollm3-3b https://www.anchorterminal.com/tools/smollm3-3b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing SmolLM3-3B is Hugging Face's open-weight dense 3B instruct model with switchable reasoning, tool calling and a 65,536-token native context, published in BF16 safetensors under Apache 2.0 with its training data and recipes.