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 Kimi-K3.1-Pro

120 open-weight models that do the same job as Kimi-K3.1-Pro (2.78T 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
moonshotai logo

Kimi-K3.1-Pro

moonshotai·Vision

≈1701 GB

Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series.

2.78T1M ctx kimi-k3.1-pro
60.9KNov 2026gguf
--vram
any
--gpus
--quant
  1. Qwen logo≈3.0 GB

    In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models.

    3.8B125K ctx Qwen Research License
    1.9MJan 2025ollama
    • Same category
    • Smaller (3.8B vs 2.78T)
    • Widely used
    vs
  2. Qwen logo≈22 GB

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

    33.4B256K ctx Apache 2.0
    217.3KOct 2025ollama
    • Same category
    • Smaller (33.4B vs 2.78T)
    • Commercial use OK
    vs
  3. google logo

    gemma-4-26B-A4B

    google·Vision

    ≈18 GB

    Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.

    26.5BA4B256K ctx Apache 2.0
    66.6KMar 2026gguf
    • Same category
    • Smaller (26.5B vs 2.78T)
    • Commercial use OK
    vs
  4. CohereLabs logo

    North-Micro-Vision-Instruct

    CohereLabs·Vision

    ≈2.9 GB

    North Micro Vision Instruct is a 2.4B-parameter open-weight vision-language model with native-resolution image support, released under the Apache 2.0 license. It is designed as a compact foundation for prototyping, task-specific fine-tuning, and specialized multimodal applications.

    2.5B500K ctx Apache 2.0
    16KAug 2026
    • Same category
    • Smaller (2.5B vs 2.78T)
    • Commercial use OK
    vs
  5. google logo

    gemma-3-4b-it

    google·Vision

    ≈3.7 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.

    4.3B128K ctx Gemma Terms of Use
    984.8KFeb 2025ollama
    • Same category
    • Smaller (4.3B vs 2.78T)
    vs
  6. LiquidAI logo

    LFM2.5-VL-450M

    LiquidAI·Vision

    ≈1.0 GB

    LFM2.5‑VL-450M is Liquid AI's refreshed version of the first vision-language model, LFM2-VL-450M, built on an updated backbone LFM2.5-350M and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our blog post.

    449M125K ctx lfm1.0
    43.1KApr 2026gguf
    • Same category
    • Smaller (449M vs 2.78T)
    vs
  7. google logo

    medgemma-4b-it

    google·Vision

    ≈4.1 GB

    This section describes the MedGemma model and how to use it.

    4.3B128K ctx health-ai-developer-foundations
    468.6KMay 2025ollama
    • Same category
    • Smaller (4.3B vs 2.78T)
    vs
  8. nvidia logo≈1.4 GB

    NVIDIA Nemotron Parse v1.1 is designed to understand document semantics and extract text and tables elements with spatial grounding.

    957M9K ctx NVIDIA Open Model License
    112KNov 2025
    • Same category
    • Smaller (957M vs 2.78T)
    • Commercial use OK
    vs
  9. google logo

    gemma-4-31B

    google·Vision

    ≈27 GB

    Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.

    32.7B256K ctx Apache 2.0
    43.8KMar 2026gguf
    • Same category
    • Smaller (32.7B vs 2.78T)
    • Commercial use OK
    vs
  10. 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
    134.9KOct 2025gguf
    • Same category
    • Smaller (8.8B vs 2.78T)
    • Commercial use OK
    vs
  11. NVIDIA Nemotron 3.5 Bolt 74B-A9B is a vision-language model (VLM) designed to run everyday agentic tasks locally. This is the full-precision (BF16) release of this model, intended primarily for customization and post-training rather than direct production inference.

    74.9BA9B256K ctx openmdw-1.1
    8.7KOct 2026gguf
    • Same category
    • Smaller (74.9B vs 2.78T)
    • Commercial use OK
    vs
  12. openbmb logo

    MiniCPM-V-4.6-Thinking

    openbmb·Vision

    ≈1.6 GB

    A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

    1.3B256K ctx Apache 2.0
    26.6KMay 2026gguf
    • Same category
    • Smaller (1.3B vs 2.78T)
    • Commercial use OK
    vs
  13. Qwen logo≈22 GB

    Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.

    36BA3B256K ctx Apache 2.0
    42KFeb 2026gguf
    • Same category
    • Smaller (36B vs 2.78T)
    • Commercial use OK
    vs
  14. microsoft logo

    Mage-VL-Cowork

    microsoft·Vision

    ≈4.4 GB

    Mage-VL-Cowork A Full Training Recipe to Learn Hybrid Computer Use from Evolved Harnesses

    4.7B256K ctx Apache 2.0
    5.5KOct 2026gguf
    • Same category
    • Smaller (4.7B vs 2.78T)
    • Commercial use OK
    vs
  15. nex-agi logo

    Nex-N2.6

    nex-agi·Vision

    ≈213 GB

    Nex-N2.6 is a multimodal agentic model from Nex-AGI, built on GLM-5.3-Flash. It is designed for computer use, coding, and long-horizon tasks involving tools. This repository contains the FP8-quantized weights of Nex-N2.6, with approximately 321B parameters.

    321BA18.3B1M ctx Apache 2.0
    1.4KNov 2026gguf
    • Same category
    • Smaller (321B vs 2.78T)
    • Commercial use OK
    • Newer release
    vs
  16. 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
    60.2KDec 2025gguf
    • Same category
    • Smaller (8.8B vs 2.78T)
    • Commercial use OK
    vs
  17. stepfun-ai logo

    step3

    stepfun-ai·Vision

    ≈221 GB

    Step3 is our cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning.

    321B64K ctx Apache 2.0
    48.6KJul 2025
    • Same category
    • Smaller (321B vs 2.78T)
    • Commercial use OK
    vs
  18. sensenova logo

    SenseNova-Loop-9B-Preview

    sensenova·Vision

    ≈7.2 GB

    SenseNova-Loop-9B-Preview is a multimodal language model developed for long-context and agentic workflows. It accepts text and images and generates text for applications that combine document understanding, coding, and interaction with external tools.

    9.7B256K ctx Apache 2.0
    5.5KOct 2026gguf
    • Same category
    • Smaller (9.7B vs 2.78T)
    • Commercial use OK
    vs
  19. inclusionAI logo

    Ling-3.0-flash-VL

    inclusionAI·Vision

    ≈80 GB

    We are introducing Ling-3.0-flash-VL, our next-generation native multimodal model. Built upon Ling-3.0-flash, it brings visual information into the complete process of understanding, reasoning, acting, and verification—advancing beyond image and video perception to solving real-world tasks through…

    125BA5.9B128K ctx MIT
    7.3KSept 2026gguf
    • Same category
    • Smaller (125B vs 2.78T)
    • Commercial use OK
    vs
  20. LGAI-EXAONE logo

    EXAONE-4.5-33B

    LGAI-EXAONE·Vision

    ≈23 GB

    We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality.

    34.4B256K ctx exaone
    23.4KApr 2026gguf
    • Same category
    • Smaller (34.4B vs 2.78T)
    vs
  21. meta-llama logo≈240 GB

    The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

    402BA17B1M ctx Llama 4 Community License
    13.9KApr 2025gguf
    • Same category
    • Smaller (402B vs 2.78T)
    vs
  22. nvidia logo

    LocateAnything-3B

    nvidia·Vision

    ≈3.0 GB

    LocateAnything is a vision-language model for fast and high-quality visual grounding, enabling precise object localization, dense detection, and point-based localization across diverse domains in both Enterprise Intelligence and Physical AI.

    3.8B32K ctx nvidia-license
    31.8KMar 2026gguf
    • Same category
    • Smaller (3.8B vs 2.78T)
    vs
  23. orcarouter logo

    Qwen3.8-27B-Uncensored

    orcarouter·Vision

    ≈19 GB

    One Gateway. Every Model. — Route Smarter · Ship Safer · Spend Less.

    27.8BApache 2.0
    8.3KAug 2026gguf
    • Same category
    • Smaller (27.8B vs 2.78T)
    • Commercial use OK
    vs
  24. zai-org logo

    GLM-4.6V-Flash

    zai-org·Vision

    ≈6.9 GB

    This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

    10.3B128K ctx MIT
    59.8KDec 2025gguf
    • Same category
    • Smaller (10.3B vs 2.78T)
    • Commercial use OK
    vs