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 WeMM-Video-35BA3B

120 open-weight models that do the same job as WeMM-Video-35BA3B (36.2B 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
tencent logo

WeMM-Video-35BA3B

tencent·Vision

≈23 GB

WeMM-Video-35B-A3B is the mixture-of-experts (35B total, 3B active) checkpoint in the WeMM-Video family. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.

36.2BA5B256K ctx Apache 2.0
5Nov 2026gguf
--vram
any
--gpus
--quant
  1. baidu logo≈18 GB

    The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    29.4BA3B128K ctx Apache 2.0
    12.3KJun 2025
    • Same category
    • Similar size (29.4B vs 36.2B)
    • Commercial use OK
    vs
  2. Skywork logo

    Skywork-R1V-38B

    Skywork·Vision

    ≈25 GB

    Skywork-R1V-38B is an open-weight vision model with 38.4B parameters from Skywork, published on Hugging Face.

    38.4B128K ctx MIT
    7.5KMar 2025
    • Same category
    • Similar size (38.4B vs 36.2B)
    • Commercial use OK
    vs
  3. philbert440 logo

    Qwen3.8-27B-Uncensored-Cyber

    philbert440·Vision

    ≈19 GB

    Cyber-specialized de-refusal of Qwen3.8-27B: fully open on the cyber/offensive-security domain while keeping reasoning, factual accuracy, and coherence intact. Vision tower and MTP speculative-decoding head are preserved (full multimodal, image-text-to-text).

    27.4B256K ctx Apache 2.0
    959Aug 2026gguf
    • Same category
    • Similar size (27.4B vs 36.2B)
    • Commercial use OK
    vs
  4. IMPORTANT: NEO and NEO MAX MTP GGUFS, along with complete model card detailing all the reasoning and instruct modes are here:

    27.8B256K ctx Apache 2.0
    573Aug 2026gguf
    • Same category
    • Similar size (27.8B vs 36.2B)
    • Commercial use OK
    vs
  5. Skywork logo

    Skywork-R1V3-38B

    Skywork·Vision

    ≈25 GB

    Skywork-R1V3-38B is the latest and most powerful open-source multimodal reasoning model in the Skywork-R1V series. Built on InternVL-38B, it significantly pushes the boundaries of multimodal and cross-disciplinary intelligence.

    38.4B32K ctx MIT
    1.7KJul 2025gguf
    • Same category
    • Similar size (38.4B vs 36.2B)
    • Commercial use OK
    vs
  6. tencent logo

    UI-Mate-27B

    tencent·Vision

    ≈19 GB

    Show the workflow once. Let the agent adapt it to the task at hand.

    27.4B256K ctx Apache 2.0
    553Aug 2026gguf
    • Same category
    • Similar size (27.4B vs 36.2B)
    • Commercial use OK
    vs
  7. OpenGVLab logo

    InternVL3-38B

    OpenGVLab·Vision

    ≈25 GB

    We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance.

    38.4B32K ctx Apache 2.0
    3.1KApr 2025
    • Same category
    • Similar size (38.4B vs 36.2B)
    • Commercial use OK
    vs
  8. OpenGVLab logo≈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
    2.2KAug 2025
    • Same category
    • Similar size (30.8B vs 36.2B)
    • Commercial use OK
    vs
  9. 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 36.2B)
    • Commercial use OK
    vs
  10. Skywork logo

    Skywork-R1V2-38B

    Skywork·Vision

    ≈25 GB

    Skywork-R1V2-38B is a state-of-the-art open-source multimodal reasoning model, achieving top-tier performance across multiple benchmarks: - On MMMU, it scores 73.6%, the highest among all open-source models to date.

    38.4B40K ctx MIT
    1.7KApr 2025
    • Same category
    • Similar size (38.4B vs 36.2B)
    • Commercial use OK
    vs
  11. tencent logo

    UI-Mate-democua-27B

    tencent·Vision

    ≈19 GB

    Show the workflow once. Let the agent adapt it to the task at hand.

    27.4B256K ctx Apache 2.0
    324Aug 2026gguf
    • Same category
    • Similar size (27.4B vs 36.2B)
    • Commercial use OK
    vs
  12. inclusionAI logo

    UI-Venus-1.5-30B-A3B

    inclusionAI·Vision

    ≈20 GB

    This repository contains the UI-Venus model from the report UI-Venus-1.5 Technical Report. UI-Venus 1.5 is a unified, end-to-end GUI Agent designed for robust real-world applications. The model family includes two dense (2B/8B) and one MoE (30B-A3B) variants to meet various downstream scenarios.

    31.1BA3B256K ctx Apache 2.0
    350Feb 2026gguf
    • Same category
    • Similar size (31.1B vs 36.2B)
    • Commercial use OK
    vs
  13. dealignai logo

    Gemma-4-31B-JANG_4M-CRACK

    dealignai·Vision

    ≈20 GB

    This is an updated version of the original Gemma 4 31B CRACK upload:

    20.2B256K ctx Gemma Terms of Use
    11.5KApr 2026
    • Same category
    • Similar size (20.2B vs 36.2B)
    vs
  14. 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
    • Same category
    • Similar size (19.4B vs 36.2B)
    • Commercial use OK
    vs
  15. 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
    8.5KOct 2026gguf
    • Same category
    • Larger (74.9B vs 36.2B)
    • Commercial use OK
    vs
  16. thinkingmachines logo

    Inkling-2-Mini

    thinkingmachines·Vision

    ≈17 GB

    Inkling 2 Mini is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

    26.4BA3.5B1M ctx Apache 2.0
    136Nov 2026ollama
    • Same category
    • Similar size (26.4B vs 36.2B)
    • Commercial use OK
    vs
  17. 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 36.2B)
    • Commercial use OK
    vs
  18. swiss-ai logo

    Apertus-v1.5-70B

    swiss-ai·Vision

    ≈46 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.

    72BApache 2.0
    7.1KJul 2026gguf
    • Same category
    • Similar size (72B vs 36.2B)
    • Commercial use OK
    vs
  19. 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 36.2B)
    vs
  20. Qwen logo

    Qwen3.5-9B

    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
    6.3MFeb 2026ollama
    • Same category
    • Smaller (9.7B vs 36.2B)
    • Commercial use OK
    • Widely used
    vs
  21. liuhaotian logo

    llava-v1.6-34b

    liuhaotian·Vision

    ≈22 GB

    Model type: LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: NousResearch/Nous-Hermes-2-Yi-34B

    34.8B4K ctx Apache 2.0
    15.8KJan 2024ollama
    • Same category
    • Similar size (34.8B vs 36.2B)
    • Commercial use OK
    vs
  22. baidu logo≈18 GB

    The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    29.4BA3B128K ctx Apache 2.0
    724Jun 2025
    • Same category
    • Similar size (29.4B vs 36.2B)
    • Commercial use OK
    vs
  23. 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 36.2B)
    • Commercial use OK
    vs
  24. ByteDance logo

    UniVR-34B-Planning

    ByteDance·Vision

    ≈23 GB

    UniVR is the first framework that simultaneously learns complex reasoning, fine-grained physical dynamics, and long-term planning from pure visual demonstrations — without relying on dense image-text pairs or task-specific heuristics.

    34BCC BY 4.0
    5Jul 2026
    • Same category
    • Similar size (34B vs 36.2B)
    • Commercial use OK
    vs