# A small fast cousin for sub-tasks beside a main model (slim)

> A small fast cousin for sub-tasks beside a main model: 8 companies fully do it, 18 with a limit, 90 carry the tag. Every listing in Open-weight models with the reason and a source.

- Full: https://www.anchorterminal.com/niches/open-weights.sub-task-cousin/index.md (~5,150 tokens) · this version ~1,230 tokens · JSON https://www.anchorterminal.com/niches/open-weights.sub-task-cousin/index.json · canonical https://www.anchorterminal.com/niches/open-weights.sub-task-cousin/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-15
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Four or more companies' docs show a full fit. Full fit: 8 companies, with a limit: 18, tagged: 90. Weight 8, 7 accounts.

Done when: Two models fit co-resident within the machine's memory, the cousin runs with thinking off, and the main model is not reloaded between calls.
yes: gemma-4-12b-it (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))
yes: gemma-4-e2b-it (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))
yes: gemma-4-e4b-it (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))
yes: granite-4-2-3b (International Business Machines Corporation (per IBM's naming guidance, as read for granite-guardian))
yes: ling-3-0-tiny (Ant Intelligence (Hang Zhou) Technology Co., Ltd (named as provider in the training-content summary); inclusionAI, Ant Group in the site footer of inclusion-ai.org)
yes: nemotron-3-5-bolt-e4b-4gb (NVIDIA Corporation)
yes: nemotron-3-nano-4b (NVIDIA Corporation)
yes: qwen3-4b-instruct-2507 (Alibaba Cloud (named in the licence's copyright line))
yes: qwen3-5-0-8b (Alibaba Cloud (named in the licence's copyright line))
yes: qwen3-5-2b (Alibaba Cloud (named in the licence's copyright line))
yes: qwen3-5-4b (Alibaba Cloud (named in the licence's copyright line))
yes: qwen3-coder-30b-a3b-instruct (Alibaba Cloud (named in the licence's copyright line))
yes: qwen3-vl-2b-instruct (Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder))
yes: qwen3-vl-4b-instruct (Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder))
yes: qwen3-vl-8b-instruct (Alibaba Cloud (per the pilot's RDAP check of qwen.ai; this model's files name no copyright holder))
yes: spark-x2-6-4b (XHToken (the licence's copyright line); the Hugging Face organisation's name is SparkLLM)
caveat: agents-a1-4b (Shanghai Artificial Intelligence Laboratory (the InternAgent team there, per the card's recommended system prompt and the template's default prompt); the GitHub LICENSE leaves the copyright line as the Apache template)
caveat: apodex-1-1-mini (Apodex (the site's copyright line reads 2026 Apodex))
caveat: bigbang-v1 (The Endless Frontier (endless-frontier))
caveat: darwin-36b-opus (VIDRAFT Inc. (named on vidraft.net); the card's citation names FINAL-Bench and VIDRAFT_LAB)
caveat: gemma-4-26b-a4b-it (Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author))
caveat: gemma-4-31b-it (Google LLC (the registrant of gemma.ai; the card names Google DeepMind as author))
caveat: glm-4-7-flash (JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai))
caveat: gpt-oss-20b (OpenAI (named in USAGE_POLICY and the model card; the LICENSE file's copyright line is the unfilled Apache template))
caveat: laguna-xs-2-1 (Poolside, Inc. (named in Poolside's Terms of Use))
caveat: lfm2-5-2-6b (Liquid AI, Inc. (the licensor named in the LFM Open License))
caveat: mimo-v2-6-distill-qwen-9b (Xiaomi (the card and report name Xiaomi MiMo; no LICENSE file names a copyright holder))
caveat: minicpm-o-4-5 (OpenBMB (named as the MiniCPM-o team on the technical report; the GitHub LICENSE is the unfilled Apache template))
caveat: minicpm5-2b (OpenBMB (named in the GitHub LICENSE's copyright line))
caveat: muse-glimmer-30b (Meta (the verified Hugging Face organisation is "Meta Inc.", the card names Meta Superintelligence Lab, and the licence carries no copyright line))
caveat: nanbeige-4-3-33b (BOSS Zhipin (Kanzhun Limited), unconfirmed)
caveat: nemotron-3-5-lightning-30b-a3b (NVIDIA Corporation)
caveat: nemotron-3-nano-30b-a3b (NVIDIA Corporation)
caveat: nemotron-3-nano-omni-30b-a3b-reasoning (NVIDIA Corporation)
caveat: occamy-1-0 (Accio (Accio-Lab))
caveat: ornith-1-5-35b-a3b (Ornith)
caveat: ornith-1-5-9b (Ornith)
caveat: qwen3-30b-a3b-instruct-2507 (Alibaba Cloud (named in the licence's copyright line))
caveat: qwen3-5-9b (Alibaba Cloud (named in the licence's copyright line))
caveat: qwen3-6-35b-a3b (Alibaba Cloud (named in the licence's copyright line))
caveat: qwen3-vl-30b-a3b-instruct (Alibaba Cloud (per the pilot's RDAP check of qwen.ai; this model's files name no copyright holder))
caveat: smollm3-3b (Hugging Face, Inc.)

Data: https://www.anchorterminal.com/api/v1/use-cases/open-weights.sub-task-cousin.json
