https://www.anchorterminal.com/tools/agents-a1-4b Dated changes, score moves with their causes, what our workers noticed, and reviews for Agents-A1-4B. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/agents-a1-4b#rev_3827 https://www.anchorterminal.com/tools/agents-a1-4b#rev_3827 Wed, 21 Oct 2026 00:00:00 +0000 review InternScience squashed every repository for the 4B into one commit on 14 July 2026, so earlier uploads can't be checked, and the GitHub README last changed on 16 July. It answered one of three Hugging Face discussions. The config declares a multi-token prediction layer whose weights aren't shipped, the template's default prompt fixes the date at 2026-07-14, and there's no generation_config.json for the card's sampling settings. GitHub issues weren't counted. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/agents-a1-4b#rev_3828 https://www.anchorterminal.com/tools/agents-a1-4b#rev_3828 Wed, 21 Oct 2026 00:00:00 +0000 review InternScience's own Q4_K_M GGUF is 3.4 GB with its vision projector, about 4.1 GB once a fifth is added for the runtime and context, so almost any machine runs it. FP8 and three GGUF precisions come from the publisher, and all six major runtimes load the Qwen3.5 architecture. Apache 2.0 with nothing added, commercial use free, and no gate. The only hosted option found is Featherless AI, with no price in the dossier. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/agents-a1-4b#rev_3829 https://www.anchorterminal.com/tools/agents-a1-4b#rev_3829 Wed, 21 Oct 2026 00:00:00 +0000 review Agents-A1-4B ships chat_template.jinja, which renders several tool_call blocks in one turn, and the card names the qwen3_coder parser in its vLLM and SGLang commands. How tools are declared and how calls come back is written only in the template. Thinking turns off per request through the template, though the card doesn't name the switch. Structured output isn't documented or claimed. Nobody independent has benchmarked it, and its Qwen3.5-4B base is inferred from the files. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/agents-a1-4b#rev_3830 https://www.anchorterminal.com/tools/agents-a1-4b#rev_3830 Wed, 21 Oct 2026 00:00:00 +0000 review Agents-A1-4B ships safetensors and GGUF only, with no Python in any repository, and the card's vLLM and SGLang commands build prompts from chat_template.jinja without trust_remote_code. Every weight file has a SHA-256 in the InternScience organisation. Beyond the files there is little for this lens. No safety results, no prompt-injection guidance or refusal statement, and no SECURITY.md or security.txt. The card doesn't name its base, which the dossier infers as Qwen3.5-4B. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/agents-a1-4b https://www.anchorterminal.com/tools/agents-a1-4b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Agents-A1-4B is InternScience's open-weight dense vision-language model for long-horizon agent work (search, research, instruction following and tool calling), about 4.5B parameters in the Qwen3.5 architecture with a 262,144-token context, published in BF16, FP8 and GGUF under Apache 2.0.