Niches · Open-weight models

A local assistant that calls tools in under 3 seconds

Two or three companies' docs show a full fit.

2companies, full fit
16companies, fit with a limit
90companies carry the tag
10share of the category's work
7first-hand accounts

What counts as done

The model returns tool calls with JSON arguments, running on an 8 GB GPU.

Measured, for our own tests: at least 95 percent of 30 test commands produce the right tool call with valid JSON arguments, median latency under 3 seconds on an 8 GB GPU, and zero empty replies. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: run Home Assistant Assist on a local model, a voice assistant that turns the lights off, route a spoken question to the right tool, an 8 GB GPU model that never misses a tool call

Does the job 3

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

ListingWhy
Granite 4.2 3B C
International Business Machines Corporation (per IBM's naming guidance, as read for granite-guardian)
Tool calling with OpenAI schemas is documented, enable_thinking false gives direct answers, the Q4_K_M is 2.2 GB on Ollama, and acc-26 measured 100 percent routing at 0.54 seconds mean on a 16 GB GPU. source
Qwen3.5-0.8B D
Alibaba Cloud (named in the licence's copyright line)
Card names qwen3_coder for vLLM and SGLang and Ollama declares tools, but nothing measures accuracy on 10 to 60 tools at this size; only the template shows the format. source
Qwen3.5-2B D
Alibaba Cloud (named in the licence's copyright line)
Card names qwen3_coder for vLLM and SGLang and Ollama declares tools, but nothing measures accuracy on 10 to 60 tools at this size; only the template shows the format. source

Does the job, with a limit 25

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
Native tool calling with the qwen3_coder parser and a 2.7 GB GGUF fit an 8 GB GPU, but thinking defaults on, no Ollama tag exists and no test of 30 commands was found. source
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)
acc-24 ran Assist on an RTX 3060 Ti 8 GB: 100 percent tool-call success but 3.6 seconds median, above the 3 second target; the 3-bit quant returned empty 9 of 33 times, IQ4_XS none. source
Gemma 4 26B A4B IT BB
Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)
Google's Q4_0 is 14.4 GB and Ollama's 16 GB, which does not fit an 8 GB GPU and leaves no context on 16 GB; acc-24 chose the 12B for this reason. Tools badge present. 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)
Fits any 8 GB GPU with Ollama tools support, but no 30-command test exists for E2B and acc-45 rates it well below E4B on every task. 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)
Fits an 8 GB GPU with Ollama tools support and acc-45 passed a six-step agent task, but no 30-command tool test exists for E4B and acc-26 found some Gemma builds without tool templates. 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)
acc-23 ran Home Assistant Assist on GLM-4.7 Flash through Ollama and it worked where Qwen failed; the 19 GB Ollama build exceeds an 8 to 16 GB GPU without offload, and Unsloth's Q3_K_XL is 13.8 GB. 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)
Fits a 16 GB GPU (acc-47 on an RTX 4080) but acc-47 found tool calling unreliable and long thinking too slow for Home Assistant; no off switch. source
LFM2.5-2.6B D
Liquid AI, Inc. (the licensor named in the LFM Open License)
Tool use is documented and 1.6 GB fits an 8 GB GPU, but calls come back as Pythonic lists between special tokens, thinking cannot be turned off, and a discussion calls the tool-call tokens the model's biggest problem. 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
Fits 8 GB with ling3 parsers in vLLM and llama.cpp --jinja, but there is no Ollama library entry, only a manual import, and looping is reported. source
MiMo-V2.6 Distill Qwen 9B C
Xiaomi (the card and report name Xiaomi MiMo; no LICENSE file names a copyright holder)
Fits 8 GB through Ollama's tools-badged tag, but tool-call reliability on llama.cpp is disputed in discussions and the card documents only SGLang's mimo reasoning parser. 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)
The template renders tool_call tags but the card never documents tool calling or names a parser; the Ollama build shows no tools badge. source
MiniCPM5-2B C
OpenBMB (named in the GitHub LICENSE's copyright line)
vLLM 0.29 and SGLang ship a minicpm5 parser for its XML calls and 1.6 GB fits any GPU, but thinking precedes each call, the Ollama page shows no tools badge, and discussions report a template crash on string arguments. source
NVIDIA Nemotron 3.5 Bolt E4B 4GB C
NVIDIA Corporation
Built for voice assistants: fits 8 GB, thinking off, gemma4 parser, BFCL-v3 67.3 at Q4_K_M (NVIDIA's run). No account runs 30 commands, and Ollama's e4b tag advertises 128K against NVIDIA's 64K. source
Nemotron 3 Nano 4B C
NVIDIA Corporation
Fits an 8 GB GPU with thinking off, qwen3_coder parser in vLLM and an Ollama tools badge, but BFCL v3 is 61.1 on the card and no account measures 30 commands. source
Ornith-1.5-9B C
Ornith
Fits an 8 GB GPU and Ollama's 9b tag has a tools badge, but thinking is on by default and lengthy, so the 3-second median needs the undocumented template switch. source
Qwen3-30B-A3B-Instruct-2507 C
Alibaba Cloud (named in the licence's copyright line)
Non-thinking with tools in Ollama, but 19 GB needs Unsloth's expert offload to CPU to run on an 8 GB to 16 GB GPU, and no account measures latency or 30 commands. source
Qwen3-4B-Instruct-2507 C
Alibaba Cloud (named in the licence's copyright line)
Tools are in the template and the Ollama library declares tools, but no parser is named on the card and no account measures 30 commands on an 8 GB GPU. source
Qwen3.5-4B C
Alibaba Cloud (named in the licence's copyright line)
Parsers named and Ollama declares tools, thinking off per request; no account measures 30 commands on this size, and acc-28 shows an Ollama regression printing calls as text on the family. source
Qwen3.5-9B C
Alibaba Cloud (named in the licence's copyright line)
acc-24 ran qwen3.5:9b in Home Assistant on an 8 GB GPU at 2.9 s median, but gives no success rate for it, and acc-26 found routing slow; parsers are named on the card. source
Qwen3-Coder-30B-A3B-Instruct C
Alibaba Cloud (named in the licence's copyright line)
No thinking and a named parser, but Q4_K_M is 18.6 GB, so an 8 to 16 GB GPU offloads experts; no voice-pipeline account exists. 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)
Tools in the template and Ollama declares tools, no thinking to block, 1.1 GB at Q4; the card names no parser and no account measures 30 commands. 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)
Tools in the template and Ollama declares tools, no thinking to block, 2.5 GB at Q4; the card names no parser and no account measures 30 commands. 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)
Tools in the template and Ollama declares tools, no thinking to block, 5.0 GB at Q4; the card names no parser and no account measures 30 commands. source
SmolLM3-3B C
Hugging Face, Inc.
Card names vLLM's hermes parser and thinking off, 1.9 GB fits any GPU; no account measures 30 commands, and the template renders tool results as user turns. source
Spark-X2.6-4B C
XHToken (the licence's copyright line); the Hugging Face organisation's name is SparkLLM
Aimed at agents with a named SGLang parser and thinking off per request on a 3.5 GB build, but the Ollama entry shows no tools badge and no account measures 30 commands. source

Doesn't do this job 58

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)
Nothing runs it on an Ollama or llama.cpp server: the architecture is not in llama.cpp and Ollama has no library entry. source
Apodex-1.1-mini C
Apodex (the site's copyright line reads 2026 Apodex)
The smallest publisher build is 21.7 GB, beyond an 8 to 16 GB GPU, and there is no Ollama tag. source
BigBang-v1 C
The Endless Frontier (endless-frontier)
The smallest build anywhere is 10 GB at IQ2_XXS from a third party and 21.9 GB at Q4; no Ollama entry and the card targets 8-GPU serving. source
Carbon-X C
Hugging Face (the HuggingFaceBio organisation, named Hugging Face Biology Research on the Hub)
No tool-calling training documented; the template inherits Qwen3's tool format but the card never uses it. source
Cosmos-Reason2-2B C
NVIDIA Corporation
No tool-calling documentation; the inherited Qwen3-VL template carries tools but NVIDIA never exercises it. source
Darwin-36B-Opus C
VIDRAFT Inc. (named on vidraft.net); the card's citation names FINAL-Bench and VIDRAFT_LAB
The Q4_K_M build is 21.2 GB; only the 1 to 3 bit POCKET files fit 16 GB, there is no Ollama entry and tool calling is undocumented. source
DeepSeek-V3.2 C
DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)
Cannot load on an 8 to 16 GB GPU; Ollama retired its deepseek-v3.2 entry on 15 July 2026. source
DeepSeek V4.1 Flash C
DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)
Cannot load on an 8 to 16 GB GPU; Ollama's entry is cloud-only. source
DeepSeek-V4-Flash-0731 C
DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)
Cannot load on an 8 to 16 GB GPU; Ollama retired deepseek-v4-flash on 27 August 2026. source
DiffusionGemma 26B A4B IT D
Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)
Nothing serves it on Ollama or released llama.cpp; the 16.8 GB third-party Q4 needs an unmerged branch. source
Gemma 4 31B IT BB
Google LLC (the registrant of gemma.ai; the card names Google DeepMind as author)
17.6 GB at Q4_0 exceeds an 8 to 16 GB GPU. 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)
No build fits an 8 to 16 GB GPU and Ollama has no entry. 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
Cannot load on an 8 to 16 GB GPU; no Ollama entry. source
GLM-5.3-Flash B
Z.AI Co., Ltd (named in the licence's copyright line)
Cannot load on an 8 to 16 GB GPU; Ollama's entry is cloud-only. source
gpt-oss-120b BB
OpenAI (named as publisher on the card; the openai-api listing's terms name OpenAI OpCo, LLC)
Cannot load on an 8 to 16 GB GPU. source
Hy3 B
Tencent (named in the LICENSE file's copyright line)
Cannot load on an 8 to 16 GB GPU; no Ollama entry. source
Inkling B
Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary)
Cannot load on an 8 to 16 GB GPU. source
Inkling-Small B
Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary)
Cannot load on an 8 to 16 GB GPU; no Ollama entry. source
InternVL3.5-GPT-OSS-20B-A4B-Preview D
Shanghai AI Laboratory (OpenGVLab), not named in the repository
No tool calling in the template or card. source
Kimi K3 B
Moonshot AI (the licence names Moonshot AI; the Kimi Platform terms name Moonshot AI PTE. LTD.)
Cannot load locally on a small GPU; Ollama's kimi-k3 is cloud-only. source
Kolibri-1 C
Aleph Alpha GmbH
No build fits an 8 to 16 GB GPU and Ollama has no entry. 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
No tool calling; the model takes OHLCV bars and returns forecast bars.
Laguna M.1 C
Poolside, Inc. (named in Poolside's Terms of Use; the LICENSE.md copyright line reads Poolside)
No build fits an 8 GB to 16 GB GPU.
Laguna S 2.1 C
Poolside, Inc. (named in Poolside's Terms of Use)
No build fits an 8 GB to 16 GB GPU.
Laguna XS 2.1 C
Poolside, Inc. (named in Poolside's Terms of Use)
The only quantised builds are 20 GB Q4_K_M and larger; nothing fits an 8 GB to 16 GB GPU. source
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
No tool calling; actions are plain-text crop instructions parsed by inclusionAI's Python.
MiniMax-M2.5 C
MiniMax AI (named in the licences; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)
No build fits an 8 GB to 16 GB GPU.
MiniMax-M2.7 C
MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)
No build fits an 8 GB to 16 GB GPU, and every reply opens a think block. source
MiniMax-M3.1-Flash C
MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)
No build fits an 8 GB to 16 GB GPU, and thinking is adaptive with no off switch in the template. source
Mistral Large 4 C
Mistral AI (RCS Paris 952 418 325)
No build fits an 8 GB to 16 GB GPU, and reasoning_effort has no off value. 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)
Smallest build is 16.8 GB (18 GB in Ollama), over an 8 GB GPU, and thinking cannot be turned off. source
Nanbeige4.3-33B C
BOSS Zhipin (Kanzhun Limited), unconfirmed
Smallest GGUF is 10.1 GB at IQ2_XXS; nothing at a usable bit width fits an 8 GB GPU, and there is no Ollama library entry. source
Nemotron 3.5 Lightning 30B A3B B
NVIDIA Corporation
Smallest build is 18.9 GB (Ollama 19 GB), over an 8 GB to 16 GB GPU. source
Nemotron 3 Nano 30B A3B B
NVIDIA Corporation
Smallest Ollama build is 18 GB, over an 8 GB to 16 GB GPU. source
Nemotron 3 Nano Omni 30B A3B Reasoning C
NVIDIA Corporation
Smallest build is 18.5 GB (Ollama 21 GB), over an 8 GB to 16 GB GPU. source
Nemotron 3 Super 120B A12B B
NVIDIA Corporation
No build fits an 8 GB to 16 GB GPU. source
Nemotron 3 Ultra 550B A55B B
NVIDIA Corporation
No build fits an 8 GB to 16 GB GPU; Ollama lists only a cloud tag. source
occamy-1.0 C
Accio (Accio-Lab)
Smallest GGUF is 11.7 GB, over an 8 GB GPU, and there is no Ollama library entry. source
Olmo 3 7B Think D
The Allen Institute for Artificial Intelligence (Ai2), a 501(c)(3) nonprofit, per its Responsible Use Guidelines
Not wired for OpenAI-style tools (custom functions field, no parser) and thinking cannot be turned off. source
Ornith-1.5-35B-A3B C
Ornith
Smallest build is Q4_K_M at 21.7 GB; nothing fits an 8 GB to 16 GB GPU. source
Ornith-1.5-397B C
Ornith
No build fits an 8 GB to 16 GB GPU.
Qwen3.5-122B-A10B B
Alibaba Cloud (named in the licence's copyright line)
No build fits an 8 to 16 GB GPU; the smallest Unsloth quant is 34 GB. source
Qwen3.5-397B-A17B B
Alibaba Cloud (named in the licence's copyright line)
No build fits an 8 to 16 GB GPU. source
Qwen3.6-27B B
Alibaba Cloud (named in the licence's copyright line)
IQ4_XS is 15.4 GB before 4 GB of KV at 64K, so it does not fit an 8 to 16 GB GPU, and acc-11 saw it describe actions instead of calling tools on Ollama. source
Qwen3.6-35B-A3B B
Alibaba Cloud (named in the licence's copyright line)
UD-Q4_K_XL is 22 GB, past an 8 to 16 GB GPU, and acc-23 saw the family's 35B fail tool calling on Ollama before it worked on llama.cpp. source
Qwen3.8-27B B
Alibaba Cloud (named in the licence's copyright line)
UD-IQ4_XS is 14.4 GB before 4 GB of KV at 64K; too large for an 8 GB GPU and no account measures it in a voice pipeline. source
Qwen3.8-Flash-Next C
Alibaba Cloud (Singapore) Private Limited, the registrant of qwen.ai. The licence names Qwen as copyright holder
No build fits an 8 to 16 GB GPU. source
Qwen3-Coder-Next C
Alibaba Cloud (the Qwen team's employer; no LICENSE file names a copyright holder for this model)
No build fits an 8 to 16 GB GPU; Unsloth's smallest is 19 GB at 1 bit. source
Qwen3-Omni-30B-A3B-Instruct D
Alibaba Cloud (carried from the 20 October 2026 pilot; this model's files name no copyright holder)
Tool calls are JSON in the template with no parser named, and the smallest build is 18.6 GB plus a 1.3 GB projector, past an 8 to 16 GB GPU. 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)
18.6 GB at Q4 plus projector does not fit an 8 to 16 GB GPU. 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 does not fit an 8 to 16 GB GPU. source
Qwopus3.8-27B-Flash-V2 C
Jackrong, an individual Hugging Face account
IQ4_XS is 15.4 GB before KV and the recommended mode is thinking at xhigh; no fit for an 8 GB GPU voice pipeline. source
Recursive Flint C
Recursive Superintelligence, Inc. (the Hugging Face organisation's full name)
Thinking cannot be switched off, which the pipeline cannot tolerate, and 23 GB passes an 8 to 16 GB GPU. source
Ripple-65B Preview D
Ricursive Intelligence, Inc.
Thinking cannot be turned off and nothing fits an 8 to 16 GB GPU. source
Swift 1.5 Qwen3.8-27B C
UkisAI
IQ4_XS is 15.5 GB before KV; too large for an 8 GB GPU. source
Swift 1.5 Qwen3.8-Flash-Next C
UkisAI
No build fits an 8 to 16 GB GPU. source
ThinkingCap (Qwen3.8 27B) C
BottleCap AI (named in the licence's copyright line)
IQ4_XS is 15.5 GB before KV; too large for an 8 GB GPU. source
Baidu Unlimited-OCR-2 C
Baidu, Inc.
No tool calling and no chat template. source

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

What stops agents finishing

  • Ollama template lacks tools, so the server answers 'does not support tools'
  • a 3-bit quant gets stuck in hidden reasoning and returns nothing
  • runtime regression prints the tool call as text

Around it

Before: speech-to-text.transcribe. After: home-automation.execute, text-to-speech.speak.

Where this comes from

Weight 10 of 100 in Open-weight models: 7 of 51 accounts, all from the Home Assistant forum, personal blogs and Ollama issues

The same as data: /api/v1/use-cases/open-weights.tool-calling-assistant.json, or the MCP tool get_use_case with id open-weights.tool-calling-assistant. 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.