Niches · Open-weight models

A small fast cousin for sub-tasks beside a main model

Four or more companies' docs show a full fit.

8companies, full fit
18companies, fit with a limit
90companies carry the tag
8share of the category's work
7first-hand accounts

What counts as done

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.

Measured, for our own tests: the cousin answers a routing or summary prompt correctly in under 3 seconds. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: a cheap model for title generation and routing, something small for the harness's utility calls, a planner and a coder that both fit in memory, a second-opinion reviewer model

Does the job 16

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Gemma 4 12B IT BB
Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author)
Thinking is off by default, the Google Q4_0 GGUF is 7 GB, and Ollama's gemma4:12b (7.7 GB) carries the tools and thinking badges, so it sits beside a main model. source
Gemma 4 E2B IT C
Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author)
3.35 GB Q4_0 from Google, thinking off by default, Ollama gemma4:e2b (4.6 GB) with tools and thinking badges; built for precisely this spare-memory role. source
Gemma 4 E4B IT B
Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author)
5.15 GB Q4_0 from Google, thinking off by default, Ollama gemma4:e4b (6.6 GB) with tools and thinking badges, and acc-45's agent task passed. source
Granite 4.2 3B C
International Business Machines Corporation (per IBM's naming guidance, as read for granite-guardian)
acc-26 found Granite 4 routed 33 voice prompts at 100 percent in 0.54 seconds on a 16 GB GPU; IBM ships GGUFs from 1.5 GB, Ollama has granite4.2:3b (2.2 GB) and enable_thinking false is documented. source
Ling-3.0-tiny C
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
4.8 GB Q4_K_M co-resides easily, enable_thinking false switches reasoning off per request, and an account measured 40 tokens per second on a CPU and over 200 on an RTX 4070. source
NVIDIA Nemotron 3.5 Bolt E4B 4GB C
NVIDIA Corporation
6.2 GB Q4_K_M from NVIDIA, enable_thinking false per request, a Brevity Benchmark row and an Ollama e4b tag of 7.2 GB to 7.9 GB with the tools badge. source
Nemotron 3 Nano 4B C
NVIDIA Corporation
2.8 GB Ollama tag and NVIDIA Q4_K_M GGUF, enable_thinking false per request, so it sits beside a main model in under 3 GB; English only. source
Qwen3-4B-Instruct-2507 C
Alibaba Cloud (named in the licence's copyright line)
Never thinks, 2.5 GB Ollama 4b-instruct tag with the tools badge, 262K context; a routing or summary call needs no switch. source
Qwen3.5-0.8B D
Alibaba Cloud (named in the licence's copyright line)
Thinking is off by default; the card warns this size falls into thinking loops if you turn it on. Ollama qwen3.5:0.8b is 1.0 GB with the tools badge, so it sits beside a main model. source
Qwen3.5-2B D
Alibaba Cloud (named in the licence's copyright line)
Thinking is off by default; the card warns this size falls into thinking loops if you turn it on. Ollama qwen3.5:2b is 2.7 GB with the tools badge, so it sits beside a main model. source
Qwen3.5-4B C
Alibaba Cloud (named in the licence's copyright line)
Thinking switched off per request with enable_thinking false, Ollama qwen3.5:4b at about 3 GB with the tools badge, 2 GB of KV at 64K. source
Qwen3-Coder-30B-A3B-Instruct C
Alibaba Cloud (named in the licence's copyright line)
No thinking mode, 19 GB Ollama tag with the tools badge; acc-51 kept it resident beside a 32B planner at about 40 GB total. source
Qwen3-VL-2B-Instruct C
Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder)
No thinking mode, publisher Q4_K_M GGUF of 1.1 GB, Ollama qwen3-vl:2b-instruct at 1.9 GB with the tools badge. source
Qwen3-VL-4B-Instruct D
Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder)
No thinking mode, publisher Q4_K_M GGUF of 2.5 GB, Ollama qwen3-vl:4b-instruct at 3.3 GB with the tools badge. source
Qwen3-VL-8B-Instruct C
Alibaba Cloud (per the pilot's RDAP check of qwen.ai; this model's files name no copyright holder)
No thinking mode, publisher Q4_K_M GGUF of 5.0 GB, Ollama qwen3-vl:8b-instruct at 6.2 GB with the tools badge. source
Spark-X2.6-4B C
XHToken (the licence's copyright line); the Hugging Face organisation's name is SparkLLM
enable_thinking false or reasoning_effort low per request, publisher Q4_K_M GGUF of 3.5 GB, Ollama SparkLLM/Spark-X2.6-4B entry. source

Does the job, with a limit 26

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Agents-A1-4B C
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
2.7 GB Q4_K_M build from the publisher and enable_thinking false in the template, but thinking is on by default and the card never documents the switch; no Ollama entry. source
Apodex-1.1-mini C
Apodex (the site's copyright line reads 2026 Apodex)
A 21.7 GB Q4_K_M GGUF fits 25 GB of spare memory and enable_thinking false is in the template, but thinking is on by default, the card does not document the switch and there is no Ollama entry. source
BigBang-v1 C
The Endless Frontier (endless-frontier)
No publisher GGUF; bartowski's Q4_K_M is 21.9 GB and the template's enable_thinking switch is undocumented on the card. Thinking defaults on. source
Darwin-36B-Opus C
VIDRAFT Inc. (named on vidraft.net); the card's citation names FINAL-Bench and VIDRAFT_LAB
Publisher GGUFs down to IQ1_M (8.2 GB) exist and enable_thinking false is in the template, but the card presents it as an always-thinking reasoning model and never names the switch. source
Gemma 4 26B A4B IT BB
Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)
Thinking off by default and an Ollama tag with tools, but the Q4_0 build is 14.4 GB (16 GB on Ollama), so it needs the top of the 2 to 25 GB spare band. source
Gemma 4 31B IT BB
Google LLC (the registrant of gemma.ai; the card names Google DeepMind as author)
Thinking off by default and an Ollama tag with tools, but 17.6 to 19 GB at Q4 uses most of a 25 GB spare band; a 31B dense is slow for a 3 second routing reply. source
GLM-4.7-Flash B
JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai)
enable_thinking false is in the template and Unsloth says 24 GB of memory at 4-bit, but 17.5 to 19 GB of weights takes most of a 25 GB spare band. source
gpt-oss-20b B
OpenAI (named in USAGE_POLICY and the model card; the LICENSE file's copyright line is the unfilled Apache template)
12 to 14 GB fits a 25 GB spare band and reasoning low is cheap, but thinking cannot be switched off, so a routing reply still carries an analysis channel. source
Laguna XS 2.1 C
Poolside, Inc. (named in Poolside's Terms of Use)
Thinking is off by default and 3B are active, but the smallest build is 20 GB, at the top of the spare-memory range. source
LFM2.5-2.6B D
Liquid AI, Inc. (the licensor named in the LFM Open License)
1.6 GB at Q4_0 and an Ollama entry with tools, but the card says it always thinks and the template forces a think tag, so routing calls carry reasoning time. source
MiMo-V2.6 Distill Qwen 9B C
Xiaomi (the card and report name Xiaomi MiMo; no LICENSE file names a copyright holder)
6.6 GB and enable_thinking false empties the think block, but it is an SFT checkpoint meant for RL and non-stop generation is reported. source
MiniCPM-o 4.5 C
OpenBMB (named as the MiniCPM-o team on the technical report; the GitHub LICENSE is the unfilled Apache template)
Q4_0 is 4.8 GB and the template empties the think block on enable_thinking false, but tool calling is undocumented and the Ollama build carries only a vision badge. source
MiniCPM5-2B C
OpenBMB (named in the GitHub LICENSE's copyright line)
1.56 GB Q4_K_M and an Ollama entry, but every answer opens with reasoning; the template accepts enable_thinking false while the card documents only Think mode, and discussions report loops. source
Muse Glimmer 30B BB
Meta (the verified Hugging Face organisation is "Meta Inc.", the card names Meta Superintelligence Lab, and the licence carries no copyright line)
The 17 GB build fits a 25 GB spare budget, but reasoning_strength bottoms out at low with no off value, so a routing call still thinks. source
Nanbeige4.3-33B C
BOSS Zhipin (Kanzhun Limited), unconfirmed
enable_thinking false turns reasoning off, but the smallest usable 4-bit build is about 19 GB, most of a 25 GB spare budget. source
Nemotron 3.5 Lightning 30B A3B B
NVIDIA Corporation
enable_thinking false turns reasoning off and 3B active is fast, but the smallest build is 18.9 GB, most of a 25 GB spare budget. source
Nemotron 3 Nano 30B A3B B
NVIDIA Corporation
enable_thinking false and a reasoning_budget example on the card, 3.5B active, but 18 GB is most of a 25 GB spare budget. source
Nemotron 3 Nano Omni 30B A3B Reasoning C
NVIDIA Corporation
enable_thinking false gives an instruct mode, but the smallest GGUF is 18.5 GB, most of a 25 GB spare budget. source
occamy-1.0 C
Accio (Accio-Lab)
Thinking switches off through the Qwen3.6 template, but the smallest GGUF is 11.7 GB (IQ2_M) and a 4-bit build about 19 GB, most of a 25 GB spare budget. source
Ornith-1.5-35B-A3B C
Ornith
3B active and enable_thinking false in the template, but the card never mentions the switch and the smallest build is 21.7 GB. source
Ornith-1.5-9B C
Ornith
5.8 GB and enable_thinking false in the template, but the card does not document the switch and the model is a long thinker. source
Qwen3-30B-A3B-Instruct-2507 C
Alibaba Cloud (named in the licence's copyright line)
No thinking block at all, so routing calls answer at once, but the 4-bit build is 19 GB, most of a 25 GB spare budget. source
Qwen3.5-9B C
Alibaba Cloud (named in the licence's copyright line)
Thinking off per request and Ollama qwen3.5:9b at 6.6 GB, but acc-26 measured it over eight times slower than Granite on routing, past the 3 second bar on a 16 GB GPU. source
Qwen3.6-35B-A3B B
Alibaba Cloud (named in the licence's copyright line)
acc-36 maps a non-thinking variant to title generation beside the main model, but at 22 GB UD-Q4_K_XL it takes most of a 25 GB spare budget. source
Qwen3-VL-30B-A3B-Instruct C
Alibaba Cloud (per the pilot's RDAP check of qwen.ai; this model's files name no copyright holder)
No thinking and 3B active, but 18.6 GB at Q4 takes most of a 25 GB spare budget. source
SmolLM3-3B C
Hugging Face, Inc.
enable_thinking false per request and 1.9 GB Q4 GGUFs from ggml-org and Unsloth, but Hugging Face ships no GGUF and Ollama has no library entry. source

Doesn't do this job 44

Listings in the category that do something else, with the reason.

ListingWhy
Apertus v1.5 8B C
ETH Zurich and EPFL (the Swiss National AI Institute, named in the Acceptable Use Policy)
No publisher GGUF, no Ollama entry and no stock runtime loads the architecture; a cousin cannot be loaded beside a main model. source
Carbon-X C
Hugging Face (the HuggingFaceBio organisation, named Hugging Face Biology Research on the Hub)
Routing or summary prompts are outside its DNA training; the card's agent section makes it a tool an agent calls, not a cousin that routes. source
Cosmos-Reason2-2B C
NVIDIA Corporation
NVIDIA ships no GGUF and no thinking switch beyond a system-prompt instruction; a routing cousin is not what it is for. source
DeepSeek-V3.2 C
DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)
No small build exists; the smallest file is 161 GB. source
DeepSeek V4.1 Flash C
DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)
No small build; 233 GB minimum. source
DeepSeek-V4-Flash-0731 C
DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)
Smallest build about 103 GB; it is the main model, not a cousin. source
DiffusionGemma 26B A4B IT D
Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)
No Google quantised build, no Ollama entry, and the only local GGUF needs a llama.cpp branch; output arrives one 256-token canvas at a time. source
GLM-4.5-Air C
JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai, per the first batch's check on 21 October 2026)
The smallest build anywhere is 38 GB (UD-TQ1_0); it is a main model, not a cousin. source
GLM-5.3 B
JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai). The licence names Z.AI
No small build. source
GLM-5.3-Flash B
Z.AI Co., Ltd (named in the licence's copyright line)
Smallest build 93 GB. source
gpt-oss-120b BB
OpenAI (named as publisher on the card; the openai-api listing's terms name OpenAI OpCo, LLC)
63 GB; it is the main model. source
Hy3 B
Tencent (named in the LICENSE file's copyright line)
Smallest build 89 GB. source
Inkling B
Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary)
No small build. source
Inkling-Small B
Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary)
Smallest build 75 GB. source
InternVL3.5-GPT-OSS-20B-A4B-Preview D
Shanghai AI Laboratory (OpenGVLab), not named in the repository
No publisher GGUF, no Ollama entry, no tool template and no thinking switch. source
Kimi K3 B
Moonshot AI (the licence names Moonshot AI; the Kimi Platform terms name Moonshot AI PTE. LTD.)
No small build. source
Kolibri-1 C
Aleph Alpha GmbH
Smallest third-party build 17.6 GB at IQ1_S and 49.8 GB at Q4; 78B total is a main model. source
Kronos C
No company. Yu Shi publishes it from the GitHub account shiyu-coder and the Hugging Face user account NeoQuasar (named ShiYu), with co-authors at Tsinghua University per the paper
Not a language model; cannot answer routing or summary prompts.
Laguna M.1 C
Poolside, Inc. (named in Poolside's Terms of Use; the LICENSE.md copyright line reads Poolside)
225B total parameters, 139 GB at the smallest; cannot sit beside a main model in spare memory.
Laguna S 2.1 C
Poolside, Inc. (named in Poolside's Terms of Use)
96 GB at Q4_K_M; cannot be the second model in spare memory.
LBS-27B C
inclusionAI, Ant Group (named in the site footer of inclusion-ai.org); the work is credited to authors from Wuhan University of Technology, CASIA, Zhejiang University and Ant Group
BF16 only, 54.7 GB; not a small cousin and not a chat or routing model.
MiniMax-M2.5 C
MiniMax AI (named in the licences; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)
Smallest build is 56 GB; cannot share memory with a main model.
MiniMax-M2.7 C
MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)
Smallest build is 61 GB (UD-IQ1_M) and thinking cannot be turned off; it cannot sit beside a main model. source
MiniMax-M3.1-Flash C
MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)
A 428B model with a 129 GB smallest build; it cannot be the small cousin. source
Mistral Large 4 C
Mistral AI (RCS Paris 952 418 325)
A 1T-parameter model; no build is small enough to sit beside a main model. source
Nemotron 3 Super 120B A12B B
NVIDIA Corporation
Needs about 64 GB to 72 GB at 4 bits; it cannot be the small cousin. source
Nemotron 3 Ultra 550B A55B B
NVIDIA Corporation
A 550B model; nothing small enough to sit beside a main model. source
Olmo 3 7B Think D
The Allen Institute for Artificial Intelligence (Ai2), a 501(c)(3) nonprofit, per its Responsible Use Guidelines
Every reply opens a think block with no switch, so a routing or title call cannot skip reasoning. source
Ornith-1.5-397B C
Ornith
397B model.
Qwen3.5-122B-A10B B
Alibaba Cloud (named in the licence's copyright line)
At 34 GB even at IQ1_M it is a main model, not a cousin in 2 to 25 GB of spare memory. source
Qwen3.5-397B-A17B B
Alibaba Cloud (named in the licence's copyright line)
Over 100 GB at any precision; not a cousin. source
Qwen3.6-27B B
Alibaba Cloud (named in the licence's copyright line)
A 17 GB Q4 main model; acc-26 measured Qwen 3.6 at 26.7 s on routing prompts, far past 3 seconds. source
Qwen3.8-27B B
Alibaba Cloud (named in the licence's copyright line)
A 17 GB Q4 main model with default xhigh reasoning; acc-39 pairs it with a smaller fast model rather than using it as the cousin. source
Qwen3.8-Flash-Next C
Alibaba Cloud (Singapore) Private Limited, the registrant of qwen.ai. The licence names Qwen as copyright holder
Over 66 GB at any precision; not a cousin. source
Qwen3-Coder-Next C
Alibaba Cloud (the Qwen team's employer; no LICENSE file names a copyright holder for this model)
48 GB at Q4_K_M; a main model, not a cousin. source
Qwen3-Omni-30B-A3B-Instruct D
Alibaba Cloud (carried from the 20 October 2026 pilot; this model's files name no copyright holder)
18.6 GB at Q4 even in ggml-org's GGUF; not a cousin. source
Qwen3-VL-32B-Instruct C
Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder)
19.8 GB at Q4 with 256 KB of KV per token; a main model. source
Qwopus3.8-27B-Flash-V2 C
Jackrong, an individual Hugging Face account
A 17 GB Q4 model the card recommends with thinking on at xhigh effort; not a cousin. source
Recursive Flint C
Recursive Superintelligence, Inc. (the Hugging Face organisation's full name)
Reasoning always on and 23 GB at INT4; a routing call spends thinking tokens first. source
Ripple-65B Preview D
Ricursive Intelligence, Inc.
57 GB NVFP4 and always-on thinking; not a cousin. source
Swift 1.5 Qwen3.8-27B C
UkisAI
A 17 GB Q4 model built to think; not a cousin. source
Swift 1.5 Qwen3.8-Flash-Next C
UkisAI
Over 66 GB at any precision; not a cousin. source
ThinkingCap (Qwen3.8 27B) C
BottleCap AI (named in the licence's copyright line)
A 17 GB Q4 model tuned for shorter but still-on reasoning; not a cousin. source
Baidu Unlimited-OCR-2 C
Baidu, Inc.
Not a chat model; it has no chat template and answers only page-parsing prompts. source

28 listings in the category were added after this reading and aren't marked yet.

What stops agents finishing

  • thinking cannot be turned off, so a routing call takes 20 seconds
  • no small quantised build, so the cousin takes the main model's memory

Around it

Before: open-weights.local-coding-agent. After: coding-agents.plan-review.

Where this comes from

Weight 8 of 100 in Open-weight models: 6 of 51 accounts pair a small model with a larger one for utility or planner roles

The same as data: /api/v1/use-cases/open-weights.sub-task-cousin.json, or the MCP tool get_use_case with id open-weights.sub-task-cousin. Other jobs in this category: /api/v1/niches?category=open-weights.

Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.