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
64.6KNov 2026gguf
--vram
any
--gpus
--quant
  1. Qwen logo

    Qwen3.5-2B-Base

    Qwen·Vision

    ≈2.2 GB

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

    2.3B256K ctx Apache 2.0
    325.1KFeb 2026gguf
    • Same category
    • Smaller (2.3B vs 2.78T)
    • Commercial use OK
    vs
  2. zai-org logo

    GLM-5.3-Flash-BF16

    zai-org·Vision

    ≈213 GB

    👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.

    321BA18.3B1M ctx MIT
    21.9KAug 2026gguf
    • Same category
    • Smaller (321B vs 2.78T)
    • Commercial use OK
    vs
  3. deepseek-ai logo

    DeepSeek-V4-Flash-Vision-Exp

    deepseek-ai·Vision

    ≈182 GB

    We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.

    305BA15.2B1M ctx MIT
    30.6KAug 2026gguf
    • Same category
    • Smaller (305B vs 2.78T)
    • Commercial use OK
    vs
  4. nvidia logo

    Cosmos-Reason2-2B

    nvidia·Vision

    ≈2.5 GB

    NVIDIA Cosmos Reason 2 is an open, customizable, 2B-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.

    2.4B256K ctx NVIDIA Open Model License
    481KDec 2025gguf
    • Same category
    • Smaller (2.4B vs 2.78T)
    • Commercial use OK
    vs
  5. openbmb logo

    MiniCPM-V-4.6

    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
    192.8KApr 2026ollama
    • Same category
    • Smaller (1.3B vs 2.78T)
    • Commercial use OK
    vs
  6. Qwen logo

    Qwen3.5-9B-Base

    Qwen·Vision

    ≈7.2 GB

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

    9.7B256K ctx Apache 2.0
    266.5KFeb 2026gguf
    • Same category
    • Smaller (9.7B vs 2.78T)
    • Commercial use OK
    vs
  7. omlab logo

    VLX-Seek-1.5-10B

    omlab·Vision

    ≈7.4 GB

    VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios.

    10B256K ctx Apache 2.0
    82.9KJul 2026gguf
    • Same category
    • Smaller (10B vs 2.78T)
    • Commercial use OK
    vs
  8. Qwen logo≈5.8 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.

    8.3B125K ctx Apache 2.0
    5.3MJan 2025ollama
    • Same category
    • Smaller (8.3B vs 2.78T)
    • Commercial use OK
    • Widely used
    vs
  9. black-forest-labs logo

    flux-3-image-klein-pup

    black-forest-labs·Vision

    ≈7.1 GB

    FLUX 3 Image Klein Prompt Upsampler is a 9B vision-language model that expands a short image request into the detailed prompt FLUX 3 Image Klein works best with. It takes the request, up to 10 reference images and an optional list of bounding boxes, and returns one prompt.

    9.4B256K ctx Apache 2.0
    38.7KOct 2026gguf
    • Same category
    • Smaller (9.4B vs 2.78T)
    • Commercial use OK
    vs
  10. tencent logo

    WeVisOne-VL-4B

    tencent·Vision

    ≈4.5 GB

    WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…

    4.8B256K ctx Apache 2.0
    35.8KOct 2026gguf
    • Same category
    • Smaller (4.8B vs 2.78T)
    • Commercial use OK
    vs
  11. Cloudflare logo

    clef-flash

    Cloudflare·Vision

    ≈7.1 GB

    Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass.

    9.4B256K ctx Apache 2.0
    33.3KSept 2026ollama
    • Same category
    • Smaller (9.4B vs 2.78T)
    • Commercial use OK
    vs
  12. XiaomiMiMo logo

    MiMo-V2.6-Distill-Qwen-9B

    XiaomiMiMo·Vision

    ≈7.1 GB

    MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data. It covers coding, general-purpose agent tasks, visual coding, and cybersecurity.

    9.4B256K ctx MIT
    36KSept 2026gguf
    • Same category
    • Smaller (9.4B vs 2.78T)
    • Commercial use OK
    vs
  13. LiquidAI logo

    LFM3-VL-2B

    LiquidAI·Vision

    ≈2.0 GB

    LFM3-VL-2B is a vision-language model for on-device visual understanding. It takes text, images, and video as input, and combines the LFM3 language model with a new in-house vision encoder.

    1.9B125K ctx lfm1.0
    29.8KOct 2026ollama
    • Same category
    • Smaller (1.9B vs 2.78T)
    vs
  14. LiquidAI logo

    LFM2.5-VL-3B

    LiquidAI·Vision

    ≈2.8 GB

    LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training.

    3.1B32K ctx lfm1.0
    45.2KAug 2026gguf
    • Same category
    • Smaller (3.1B vs 2.78T)
    vs
  15. internlm logo

    Intern-S2-397B

    internlm·Vision

    ≈241 GB

    💻Github Repo • 🤗HF Model Collections • 🤖ModelScope Collections • 💬Online Chat

    403BA24.4B256K ctx Apache 2.0
    1.1KSept 2026gguf
    • Same category
    • Smaller (403B vs 2.78T)
    • Commercial use OK
    vs
  16. google logo

    medgemma-1.5-4b-it

    google·Vision

    ≈4.1 GB

    * License: The use of MedGemma is governed by the Health AI Developer Foundations terms of use. MedGemma has not been evaluated or optimized for multi-turn applications.

    4.3B128K ctx health-ai-developer-foundations
    194.2KJan 2026ollama
    • Same category
    • Smaller (4.3B vs 2.78T)
    vs
  17. h2oai logo

    h2o-lightning-4b

    h2oai·Vision

    ≈4.2 GB

    H2O-Lightning-4B is a 4B-parameter decision model from H2O.ai, built on Qwen/Qwen3.5-4B. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation) and about images that come with the record (photos, screenshots, scanned documents, charts).

    4.5B256K ctx Apache 2.0
    26.2KOct 2026gguf
    • Same category
    • Smaller (4.5B vs 2.78T)
    • Commercial use OK
    vs
  18. 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
    418.4KSept 2025ollama
    • Same category
    • Smaller (31.1B vs 2.78T)
    • Commercial use OK
    vs
  19. nvidia logo

    Nemotron-3.5-Parse

    nvidia·Vision

    ≈1.2 GB

    Nemotron 3.5 Parse is a document image parser that produces structured, machine-readable text with semantic layout classes, bounding boxes, and reading order. It combines a C-RADIOv4-SO400M vision encoder with a 10-layer mBART decoder that consumes the visual sequence as a causal prefix.

    631M16K ctx Custom licence
    27.1KSept 2026gguf
    • Same category
    • Smaller (631M vs 2.78T)
    • Commercial use OK
    vs
  20. tencent logo

    WeVisOne-VL-2B

    tencent·Vision

    ≈2.8 GB

    WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…

    2.4B256K ctx Apache 2.0
    18.2KOct 2026gguf
    • Same category
    • Smaller (2.4B vs 2.78T)
    • Commercial use OK
    vs
  21. ibm-granite logo

    granite-vision-4.1-4b

    ibm-granite·Vision

    ≈3.5 GB

    Model Summary: Granite Vision 4.1 4B is a vision-language model (VLM) that delivers frontier-level performance on structured document extraction tasks — chart extraction, table extraction, and semantic key-value pair extraction — in a compact 4B parameter footprint, providing a lightweight…

    4B128K ctx Apache 2.0
    72.1KApr 2026gguf
    • Same category
    • Smaller (4B vs 2.78T)
    • Commercial use OK
    vs
  22. LiquidAI logo

    d1-3B

    LiquidAI·Vision

    ≈2.8 GB

    d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in one forward pass with zero output tokens.

    3.1B32K ctx lfm1.0
    19.7KOct 2026gguf
    • Same category
    • Smaller (3.1B vs 2.78T)
    vs
  23. LiquidAI logo

    d1-2B

    LiquidAI·Vision

    ≈2.0 GB

    d1-2B is a decision model for text, pictures, and video, built on LFM3-VL-2B. It returns calibrated answers in one forward pass, without generating tokens.

    1.9B125K ctx lfm1.0
    16.8KOct 2026ollama
    • Same category
    • Smaller (1.9B vs 2.78T)
    vs
  24. Qwen logo≈142 GB

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

    236BA22B256K ctx Apache 2.0
    318.9KSept 2025ollama
    • Same category
    • Smaller (236B vs 2.78T)
    • Commercial use OK
    vs