selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

Alternatives to Groot-19B-A3B-261023

120 open-weight models that do the same job as Groot-19B-A3B-261023 (19.4B vision), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.

the original
GrootTeam logo

Groot-19B-A3B-261023

GrootTeam·Vision

≈13 GB

Groot is a family of open-weight reasoning models for complex real-world tasks. The models are compact and easy to deploy, strong on reasoning and tool-using workloads, and efficient with token budgets.

19.4BA3B256K ctx Apache 2.0
3.3KOct 2026gguf
--vram
any
--gpus
--quant
  1. zai-org logo≈16 GB

    We launch a new generation of CogVLM2 series of models and open source two models built with Meta-Llama-3-8B-Instruct. Compared with the previous generation of CogVLM open source models, the CogVLM2 series of open source models have the following improvements:

    19.5B8K ctx cogvlm2
    5.4KMay 2024
    • Same category
    • Similar size (19.5B vs 19.4B)
    vs
  2. deepseek-ai logo

    deepseek-vl2-small

    deepseek-ai·Vision

    ≈11 GB

    Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL.

    16.1BA3.1B4K ctx DeepSeek License
    5.2KDec 2024
    • Same category
    • Similar size (16.1B vs 19.4B)
    vs
  3. naver-hyperclovax logo

    HyperCLOVAX-SEED-Think-32B

    naver-hyperclovax·Vision

    ≈23 GB

    HyperCLOVA X SEED 32B Think is an updated vision-language thinking model that advances the SEED Think 14B line beyond simple scaling, pairing a unified vision-language Transformer backbone with a reasoning-centric training recipe.

    33.3B128K ctx hyperclovax
    7.3KDec 2025gguf
    • Same category
    • Similar size (33.3B vs 19.4B)
    vs
  4. Qwen logo≈6.8 GB

    Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

    8.8B256K ctx Apache 2.0
    135.3KOct 2025gguf
    • Same category
    • Smaller (8.8B vs 19.4B)
    • Commercial use OK
    vs
  5. Qwen logo≈20 GB

    Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

    31.1BA3B256K ctx Apache 2.0
    7.1KSept 2025gguf
    • Same category
    • Similar size (31.1B vs 19.4B)
    • Commercial use OK
    vs
  6. rhymes-ai logo

    Aria

    rhymes-ai·Vision

    ≈18 GB

    [Dec 1, 2024] We have released the base models (with native multimodal pre-training) for Aria (Aria-Base-8K and Aria-Base-64K) for research purposes and continue training.

    25.3BA4.6B64K ctx Apache 2.0
    18.8KSept 2024
    • Same category
    • Similar size (25.3B vs 19.4B)
    • Commercial use OK
    vs
  7. OpenGVLab logo

    InternVL3_5-30B-A3B

    OpenGVLab·Vision

    ≈20 GB

    We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series.

    30.8BA3B40K ctx Apache 2.0
    7.9KAug 2025gguf
    • Same category
    • Similar size (30.8B vs 19.4B)
    • Commercial use OK
    vs
  8. moondream logo

    moondream3.1-9B-A2B

    moondream·Vision

    ≈6.5 GB

    Moondream 3.1 is a vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). It delivers state-of-the-art visual reasoning and detection while staying fast and cheap to deploy.

    9.3BA2Bmoondream-model-license-1.0
    8.3KJun 2026
    • Same category
    • Smaller (9.3B vs 19.4B)
    vs
  9. tencent logo

    Hy-Embodied-VLM-1.0

    tencent·Vision

    ≈19 GB

    Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world.

    30.5B32K ctx Apache 2.0
    553Jul 2026
    • Same category
    • Similar size (30.5B vs 19.4B)
    • Commercial use OK
    vs
  10. bottlecapai logo

    ThinkingCap-Qwen3.6-27B

    bottlecapai·Vision

    ≈19 GB

    Capability of Qwen3.6-27B with 50% less thinking tokens on average, and over 90% less in best cases. Achieved via finetuning Qwen3.6-27B (Qwen Team, 2026) with state-of-the-art algorithms on a curated set of problems of various domains and difficulty.

    27.4B256K ctx Apache 2.0
    203Jul 2026gguf
    • Same category
    • Similar size (27.4B vs 19.4B)
    • Commercial use OK
    vs
  11. inclusionAI logo

    UI-Venus-2-9B

    inclusionAI·Vision

    ≈6.8 GB

    UI-Venus-2 is a general-purpose foundation GUI agent designed to operate across mobile applications, web platforms, and desktop operating systems through a unified closed-loop reasoning–action framework: the agent observes the current interface, reasons about the task state, executes an action, and…

    9B256K ctx Unknown licence
    6.5KAug 2026gguf
    • Same category
    • Smaller (9B vs 19.4B)
    vs
  12. nvidia logo

    Cosmos-Reason2-8B

    nvidia·Vision

    ≈6.8 GB

    NVIDIA Cosmos Reason 2 is an open, customizable, 8B-parameter reasoning vision language model (VLM) for physical AI and robotics that enables robots and vision AI agents to reason like humans, using prior knowledge, physics understanding and common sense to understand and act in the real world.

    8.8B256K ctx NVIDIA Open Model License
    60KDec 2025gguf
    • Same category
    • Smaller (8.8B vs 19.4B)
    • Commercial use OK
    vs
  13. swiss-ai logo

    Apertus-v1.5-8B

    swiss-ai·Vision

    ≈6.9 GB

    Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multilingual, multimodal, fully open, and transparent AI.

    8.9BApache 2.0
    9.3KJul 2026gguf
    • Same category
    • Smaller (8.9B vs 19.4B)
    • Commercial use OK
    vs
  14. google logo

    gemma-3-27b-pt

    google·Vision

    ≈21 GB

    Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

    27.4BGemma Terms of Use
    7.2KMar 2025gguf
    • Same category
    • Similar size (27.4B vs 19.4B)
    vs
  15. allenai logo

    Molmo2-8B

    allenai·Vision

    ≈6.8 GB

    Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding.

    8.7B36K ctx Apache 2.0
    53.3KDec 2025gguf
    • Same category
    • Smaller (8.7B vs 19.4B)
    • Commercial use OK
    vs
  16. datalab-to logo

    lift

    datalab-to·Vision

    ≈7.2 GB

    lift is a structured extraction model from Datalab that pulls structured JSON out of PDFs and images. Pass any JSON schema and lift returns a JSON object matching it, using schema-constrained decoding to guarantee valid, well-typed output.

    9.7B256K ctx OpenRAIL
    4.6KJun 2026gguf
    • Same category
    • Smaller (9.7B vs 19.4B)
    vs
  17. google logo

    gemma-3-12b-pt

    google·Vision

    ≈11 GB

    Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

    12.2BGemma Terms of Use
    21.7KMar 2025gguf
    • Same category
    • Similar size (12.2B vs 19.4B)
    vs
  18. zai-org logo

    GLM-4.1V-9B-Thinking

    zai-org·Vision

    ≈6.9 GB

    📖 View the GLM-4.1V-9B-Thinking paper . 📍 Using GLM-4.1V-9B-Thinking API at Zhipu Foundation Model Open Platform

    10.3B64K ctx MIT
    37.8KJun 2025gguf
    • Same category
    • Similar size (10.3B vs 19.4B)
    • Commercial use OK
    vs
  19. Agnes-AI logo

    Agnes-3.0-Flash

    Agnes-AI·Vision

    ≈22 GB

    This repository contains an earlier open-weight Preview checkpoint of Agnes 3.0 Flash. It is distinct from the newer production/API checkpoint listed on Artificial Analysis. The Preview release has 33B parameters and a context window of 262,144 tokens.

    33.1B256K ctx Apache 2.0
    468Sept 2026gguf
    • Same category
    • Similar size (33.1B vs 19.4B)
    • Commercial use OK
    vs
  20. sensenova logo

    SenseNova-Loop-9B

    sensenova·Vision

    ≈7.2 GB

    🔥 2026-11-17: We release SenseNova-Loop-9B, with model weights and code available to the community.

    9.4B512K ctx Apache 2.0
    1.6KNov 2026gguf
    • Same category
    • Smaller (9.4B vs 19.4B)
    • Commercial use OK
    • Newer release
    vs
  21. llm-jp logo

    llm-jp-4-vl-9b

    llm-jp·Vision

    ≈6.9 GB

    Compared with the earlier LLM-jp-4-VL 9B beta, the new model is trained on datasets that have no license or terms-of-use issues for commercial use. It is also enhanced to generate a reasoning trace before a final answer.

    9.1B64K ctx Apache 2.0
    4.2KAug 2026gguf
    • Same category
    • Smaller (9.1B vs 19.4B)
    • Commercial use OK
    vs
  22. baidu logo≈19 GB

    Here is an example of how to use the transformers library for inference:

    29.7BA3B128K ctx Apache 2.0
    1.5KNov 2025
    • Same category
    • Similar size (29.7B vs 19.4B)
    • Commercial use OK
    vs
  23. FreedomIntelligence logo

    HuatuoGPT-3-9B

    FreedomIntelligence·Vision

    ≈7.1 GB

    HuatuoGPT-3-9B is a medical LLM built on Qwen3.5-9B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning.

    9.4B256K ctx Apache 2.0
    2.1KSept 2026gguf
    • Same category
    • Smaller (9.4B vs 19.4B)
    • Commercial use OK
    vs
  24. OpenGVLab logo

    InternVL3_5-8B

    OpenGVLab·Vision

    ≈6.7 GB

    We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series.

    8.5B40K ctx Apache 2.0
    96.9KAug 2025gguf
    • Same category
    • Smaller (8.5B vs 19.4B)
    • Commercial use OK
    vs