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 Mistral-Large-4-1T-A52B

120 open-weight models that do the same job as Mistral-Large-4-1T-A52B (1T 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
mistralai logo

Mistral-Large-4-1T-A52B

mistralai·Vision

≈602 GB

Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's…

1TA52B1M ctx Custom licence
20.6KSept 2026gguf
--vram
any
--gpus
--quant
  1. Cloudflare logo

    clef

    Cloudflare·Vision

    ≈19 GB

    Clef is a 27B 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.

    27.4B256K ctx Apache 2.0
    79.3KSept 2026ollama
    • Same category
    • Smaller (27.4B vs 1T)
    • Commercial use OK
    vs
  2. OpenGVLab logo

    InternVL3_5-241B-A28B

    OpenGVLab·Vision

    ≈145 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.

    241BA28B40K ctx Apache 2.0
    573Aug 2025gguf
    • Same category
    • Smaller (241B vs 1T)
    • Commercial use OK
    vs
  3. Qwen logo≈2.6 GB

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

    2.1B256K ctx Apache 2.0
    1.2MOct 2025ollama
    • Same category
    • Smaller (2.1B vs 1T)
    • Commercial use OK
    vs
  4. interfaze-ai logo

    interfaze-1-lite

    interfaze-ai·Vision

    ? GB

    Interfaze 1.1 Lite is a mixture-of-architectures (MoA) model for developer workloads: reading documents, transcribing speech, locating objects and interface elements, and answering over all of it with structured output.

    ?Binterfaze-open
    133Oct 2026
    • Same category
    • Newer release
    vs
  5. meta-models logo

    Muse-Glimmer-30B-assistant

    meta-models·Vision

    ≈2.2 GB

    Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware.

    2.6B128K ctx Apache 2.0
    90.3KAug 2026
    • Same category
    • Smaller (2.6B vs 1T)
    • Commercial use OK
    vs
  6. 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
    321.5KFeb 2026gguf
    • Same category
    • Smaller (2.3B vs 1T)
    • Commercial use OK
    vs
  7. 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
    194.5KApr 2026ollama
    • Same category
    • Smaller (1.3B vs 1T)
    • Commercial use OK
    vs
  8. 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
    7.8KSept 2026gguf
    • Same category
    • Smaller (125B vs 1T)
    • Commercial use OK
    vs
  9. 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
    475.6KDec 2025gguf
    • Same category
    • Smaller (2.4B vs 1T)
    • Commercial use OK
    vs
  10. 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
    266.8KFeb 2026gguf
    • Same category
    • Smaller (9.7B vs 1T)
    • Commercial use OK
    vs
  11. 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
    5.2MJan 2025ollama
    • Same category
    • Smaller (8.3B vs 1T)
    • Commercial use OK
    • Widely used
    vs
  12. 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
    36.4KOct 2026gguf
    • Same category
    • Smaller (4.8B vs 1T)
    • Commercial use OK
    • Newer release
    vs
  13. 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
    73.4KJul 2026gguf
    • Same category
    • Smaller (10B vs 1T)
    • Commercial use OK
    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
    54.2KAug 2026gguf
    • Same category
    • Smaller (3.1B vs 1T)
    vs
  15. 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
    38.9KSept 2026gguf
    • Same category
    • Smaller (9.4B vs 1T)
    • Commercial use OK
    vs
  16. 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
    31KOct 2026gguf
    • Same category
    • Smaller (9.4B vs 1T)
    • Commercial use OK
    • Newer release
    vs
  17. 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
    30.7KOct 2026ollama
    • Same category
    • Smaller (1.9B vs 1T)
    • Newer release
    vs
  18. 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
    32.7KSept 2026ollama
    • Same category
    • Smaller (9.4B vs 1T)
    • Commercial use OK
    vs
  19. 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
    26.1KOct 2026gguf
    • Same category
    • Smaller (4.5B vs 1T)
    • Commercial use OK
    • Newer release
    vs
  20. Looking for a post-trained model? See the BF16 release for customization or the NVFP4 release for optimized deployment.

    124BA12Bopenmdw-1.1
    3.4KOct 2026
    • Same category
    • Smaller (124B vs 1T)
    • Commercial use OK
    • Newer release
    vs
  21. 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
    399.2KSept 2025ollama
    • Same category
    • Smaller (31.1B vs 1T)
    • Commercial use OK
    vs
  22. 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
    183.5KJan 2026ollama
    • Same category
    • Smaller (4.3B vs 1T)
    vs
  23. 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
    18.5KOct 2026gguf
    • Same category
    • Smaller (2.4B vs 1T)
    • Commercial use OK
    • Newer release
    vs
  24. 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
    26.5KSept 2026gguf
    • Same category
    • Smaller (631M vs 1T)
    • Commercial use OK
    vs