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 DeskForge-Gemma4-E4B

120 open-weight models that do the same job as DeskForge-Gemma4-E4B (7.9B 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
docling-project logo

DeskForge-Gemma4-E4B

docling-project·Vision

≈5.9 GB

DeskForge-Gemma4-E4B is Gemma 4 E4B (instruction-tuned) fine-tuned on 200K grounding examples from DeskForge-1M. Given a desktop screenshot and a natural-language instruction, it answers with the next action as a pyautogui call whose coordinates are fractions of the screen.

7.9B128K ctx Apache 2.0
449Oct 2026gguf
--vram
any
--gpus
--quant
  1. tencent logo

    WeMM-Video-9B

    tencent·Vision

    ≈7.7 GB

    WeMM-Video-9B is the dense 9B 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.

    10.5B256K ctx Apache 2.0
    230Nov 2026gguf
    • Same category
    • Similar size (10.5B vs 7.9B)
    • Commercial use OK
    • Newer release
    vs
  2. maritaca-ai logo

    S5-nano

    maritaca-ai·Vision

    ≈4.3 GB

    S5-nano is a 4B-parameter model from Maritaca AI. It has two modes:

    4.7B256K ctx Apache 2.0
    2.3KNov 2026gguf
    • Same category
    • Similar size (4.7B vs 7.9B)
    • Commercial use OK
    • Newer release
    vs
  3. google logo

    gemma-4-26B-A4B-it

    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.

    25.8BA4B256K ctx Apache 2.0
    4.8MMar 2026ollama
    • Same category
    • Larger (25.8B vs 7.9B)
    • Commercial use OK
    • Widely used
    vs
  4. numind logo≈5.8 GB

    NuMarkdown-8B-Thinking is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications. It generates thinking tokens to figure out the layout of the document before generating the Markdown file.

    8.3B125K ctx MIT
    845Jul 2025gguf
    • Same category
    • Similar size (8.3B vs 7.9B)
    • Commercial use OK
    vs
  5. google logo

    translategemma-4b-it

    google·Vision

    ≈4.5 GB

    TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages.

    5B128K ctx Gemma Terms of Use
    10.5KJan 2026ollama
    • Same category
    • Similar size (5B vs 7.9B)
    vs
  6. 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 7.9B)
    • Widely used
    vs
  7. ByteDance-Seed logo

    UI-TARS-7B-DPO

    ByteDance-Seed·Vision

    ≈5.8 GB

    UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities.

    8.3B32K ctx Apache 2.0
    2.8KJan 2025gguf
    • Same category
    • Similar size (8.3B vs 7.9B)
    • Commercial use OK
    vs
  8. OpenGVLab logo

    InternVL3-8B-Instruct

    OpenGVLab·Vision

    ≈5.7 GB

    This is the SFT version of InternVL3-8B, which has undergone native multimodal pre-trainin and SFT but has not undergone MPO. If you're unsure which version to use, please use the InternVL3-8B version.

    7.9B32K ctx Apache 2.0
    936Apr 2025gguf
    • Same category
    • Similar size (7.9B vs 7.9B)
    • Commercial use OK
    vs
  9. zai-org logo

    Glyph

    zai-org·Vision

    ≈6.9 GB

    Glyph is a framework for scaling the context length through visual-text compression. Instead of extending token-based context windows, Glyph renders long textual sequences into images and processes them using vision–language models (VLMs).

    10.3B128K ctx MIT
    2.4KOct 2025gguf
    • Same category
    • Similar size (10.3B vs 7.9B)
    • Commercial use OK
    vs
  10. XiaomiMiMo logo

    MiMo-VL-7B-SFT

    XiaomiMiMo·Vision

    ≈6.5 GB

    In this report, we share our efforts to build a compact yet powerful VLM, MiMo-VL-7B. MiMo-VL-7B comprises (1) a native resolution ViT encoder that preserves fine-grained visual details, (2) an MLP projector for efficient cross-modal alignment, and (3) our MiMo-7B language model, specifically…

    8.3B125K ctx MIT
    988May 2025gguf
    • Same category
    • Similar size (8.3B vs 7.9B)
    • Commercial use OK
    vs
  11. allenai logo

    Molmo2-ER

    allenai·Vision

    ≈4.5 GB

    Molmo2-ER (Embodied Reasoning) is a 4B vision–language model specialized for the embodied perception skills that downstream action models depend on: scene understanding, pixel-accurate pointing, multi-image and egocentric–exocentric correspondence, and video temporal reasoning.

    4.9B16K ctx Apache 2.0
    3.5KMay 2026
    • Same category
    • Similar size (4.9B vs 7.9B)
    • Commercial use OK
    vs
  12. GroundingPI logo

    GroundAnything-VLM

    GroundingPI·Vision

    ≈4.5 GB

    Model family: GroundAnything — DLM / parallel decoding · GroundAnything-VLM — autoregressive.

    4.8B256K ctx apache-2.0-with-upstream-kimi-k3
    1.2KSept 2026gguf
    • Same category
    • Similar size (4.8B vs 7.9B)
    • Commercial use OK
    vs
  13. meta-llama logo≈8.1 GB

    The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text \+ images in / text out).

    10.7B128K ctx Llama 3.2 Community License
    53.3KSept 2024ollama
    • Same category
    • Similar size (10.7B vs 7.9B)
    vs
  14. OpenGVLab logo≈5.6 GB

    VideoChat-Flash-7B is constructed upon UMT-L (300M) and Qwen2-7B, employing only 16 tokens per frame. By leveraging Yarn to extend the context window to 128k (Qwen2's native context window is 32k), our model supports input sequences of up to approximately 10,000 frames.

    7.9B32K ctx Apache 2.0
    1.5KJan 2025
    • Same category
    • Similar size (7.9B vs 7.9B)
    • Commercial use OK
    vs
  15. NVIDIA Nemotron Nano v2 12B VL model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities.

    13.2BNVIDIA Open Model License
    16KOct 2025gguf
    • Same category
    • Similar size (13.2B vs 7.9B)
    • Commercial use OK
    vs
  16. Qwen logo

    Qwen3.5-2B

    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
    5.4MFeb 2026ollama
    • Same category
    • Smaller (2.3B vs 7.9B)
    • Commercial use OK
    • Widely used
    vs
  17. GroundingPI logo

    GroundingPI

    GroundingPI·Vision

    ≈4.5 GB

    Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control.

    4.8B256K ctx apache-2.0-with-upstream-kimi-k3
    956Sept 2026
    • Same category
    • Similar size (4.8B vs 7.9B)
    • Commercial use OK
    vs
  18. llava-hf logo

    LLaVA-NeXT-Video-7B-hf

    llava-hf·Vision

    ≈5.7 GB

    Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance:

    7.1BLlama 2 Community License
    19.5KJun 2024
    • Same category
    • Similar size (7.1B vs 7.9B)
    vs
  19. microsoft logo

    Fara1.5-4B

    microsoft·Vision

    ≈4.2 GB

    Fara1.5-4B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting structured tool calls — click, type, scroll, visit URL, web search, and so on — to complete tasks…

    4.5B256K ctx MIT
    2.8KJul 2026gguf
    • Same category
    • Similar size (4.5B vs 7.9B)
    • Commercial use OK
    vs
  20. TencentARC logo

    ARC-Hunyuan-Video-7B

    TencentARC·Vision

    ≈5.7 GB

    Please note that in our Demo, ARC-Hunyuan-Video-7B is the model consistent with the model checkpoint and the one described in the paper, while ARC-Hunyuan-Video-7B-V0 only supports video description and summarization in Chinese.

    8.6B1K ctx Unknown licence
    577Jul 2025
    • Same category
    • Similar size (8.6B vs 7.9B)
    vs
  21. google logo

    translategemma-12b-it

    google·Vision

    ≈11 GB

    TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages.

    13.2B128K ctx Gemma Terms of Use
    6.2KJan 2026ollama
    • Same category
    • Similar size (13.2B vs 7.9B)
    vs
  22. zai-org logo

    GLM-4.1V-9B-Base

    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
    3KJun 2025gguf
    • Same category
    • Similar size (10.3B vs 7.9B)
    • Commercial use OK
    vs
  23. baidu logo

    Qianfan-VL-8B

    baidu·Vision

    ≈6.7 GB

    This repository contains models presented in the paper Qianfan-OCR: A Unified End-to-End Model for Document Intelligence.

    8.8B32K ctx Custom licence
    367Sept 2025
    • Same category
    • Similar size (8.8B vs 7.9B)
    vs
  24. facebook logo

    Perception-LM-8B

    facebook·Vision

    ≈7.4 GB

    Perception Language Model (PLM) is a state-of-the-art, fully open and reproducible MLLM for transparent research in image and video understanding. It was introduced in "PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding".

    9.8Bfair-noncommercial-research
    3.2KApr 2025
    • Same category
    • Similar size (9.8B vs 7.9B)
    vs