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-9B

120 open-weight models that do the same job as WeMM-Video-9B (10.5B 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-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
--vram
any
--gpus
--quant
  1. OpenGVLab logo

    InternVL3-8B-hf

    OpenGVLab·Vision

    ≈5.7 GB

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

    7.9B32K ctx Qwen License
    27.4KApr 2025
    • Same category
    • Similar size (7.9B vs 10.5B)
    vs
  2. stepfun-ai logo

    Step3-VL-10B-Base

    stepfun-ai·Vision

    ≈7.7 GB

    STEP3-VL-10B is a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. Despite its compact 10B parameter footprint, STEP3-VL-10B excels in visual perception, complex reasoning, and human-centric alignment.

    10.2B40K ctx Apache 2.0
    380Jan 2026gguf
    • Same category
    • Similar size (10.2B vs 10.5B)
    • Commercial use OK
    vs
  3. 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
    • Same category
    • Similar size (7.9B vs 10.5B)
    • Commercial use OK
    vs
  4. allenai logo

    MolmoWeb-8B

    allenai·Vision

    ≈6.8 GB

    Important Update! We made a few small but important updates to this HF/transformers-compatible checkpoint to ensure exact outputs to our native model checkpoint on March 29, 2026 ~6PM PST. If you downloaded this model checkpoint earlier than this time, we recommend re-downloading it.

    8.7B10K ctx Apache 2.0
    857Mar 2026
    • Same category
    • Similar size (8.7B vs 10.5B)
    • Commercial use OK
    vs
  5. OpenGVLab logo

    InternVL3_5-8B-Instruct

    OpenGVLab·Vision

    ≈6.7 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.

    8.5B40K ctx Apache 2.0
    5KAug 2025
    • Same category
    • Similar size (8.5B vs 10.5B)
    • Commercial use OK
    vs
  6. 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 10.5B)
    • Commercial use OK
    vs
  7. nvidia logo

    Cosmos-Reason1-7B

    nvidia·Vision

    ≈5.8 GB

    NVIDIA Cosmos Reason – an open, customizable, 7B-parameter reasoning vision language model (VLM) for physical AI and robotics - 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.

    8.3B125K ctx NVIDIA Open Model License
    15.7KApr 2025gguf
    • Same category
    • Similar size (8.3B vs 10.5B)
    • Commercial use OK
    vs
  8. zai-org logo

    UI2Code_N

    zai-org·Vision

    ≈6.9 GB

    UI2Code^N: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation

    10.3B64K ctx MIT
    456Nov 2025
    • Same category
    • Similar size (10.3B vs 10.5B)
    • Commercial use OK
    vs
  9. microsoft logo

    Fara-7B

    microsoft·Vision

    ≈5.8 GB

    Description: Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use. With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger…

    8.3B125K ctx MIT
    3.2KOct 2025gguf
    • Same category
    • Similar size (8.3B vs 10.5B)
    • Commercial use OK
    vs
  10. OpenMOSS-Team logo

    MOSS-VL-Base-0708

    OpenMOSS-Team·Vision

    ≈8.7 GB

    MOSS-VL is an open vision-language model family from OpenMOSS, supporting image understanding, long-video understanding, and realtime streaming interaction.

    11.3B256K ctx Apache 2.0
    110Jul 2026
    • Same category
    • Similar size (11.3B vs 10.5B)
    • Commercial use OK
    vs
  11. 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 10.5B)
    vs
  12. XiaomiMiMo logo

    MiMo-Embodied-7B

    XiaomiMiMo·Vision

    ≈6.5 GB

    MiMo-Embodied, a powerful cross-embodied vision-language model that shows state-of-the-art performance in both autonomous driving and embodied AI tasks, the first open-source VLM that integrates these two critical areas, significantly enhancing understanding and reasoning in dynamic physical…

    8.3B125K ctx MIT
    2.6KNov 2025gguf
    • Same category
    • Similar size (8.3B vs 10.5B)
    • Commercial use OK
    vs
  13. XiaomiMiMo logo

    MiMo-VL-7B-RL-2508

    XiaomiMiMo·Vision

    ≈6.5 GB

    We're excited to announce improvements to our MiMo-VL (MiMo-VL-7B-RL-2508 and MiMo-VL-7B-SFT-2508), featuring enhanced performance across multiple benchmarks, improved thinking control capabilities, and better user experience.

    8.3B125K ctx MIT
    5.7KAug 2025gguf
    • Same category
    • Similar size (8.3B vs 10.5B)
    • Commercial use OK
    vs
  14. OpenMOSS-Team logo

    MOSS-VL-Instruct-0408

    OpenMOSS-Team·Vision

    ≈8.7 GB

    MOSS-VL is an open vision-language model family from OpenMOSS, supporting image understanding, long-video understanding, and realtime streaming interaction.

    11.3B256K ctx Apache 2.0
    195Apr 2026
    • Same category
    • Similar size (11.3B vs 10.5B)
    • Commercial use OK
    vs
  15. lmms-lab logo≈6.7 GB

    LLaVA-OneVision-1.5 is a fully open-source family of large multimodal models (LMMs) built to democratize multimodal training. Trained on native‑resolution images, it delivers state‑of‑the‑art performance at substantially lower cost.

    8.5B32K ctx Apache 2.0
    2.6KSept 2025
    • Same category
    • Similar size (8.5B vs 10.5B)
    • Commercial use OK
    vs
  16. meta-llama logo

    Llama-3.2-11B-Vision

    meta-llama·Vision

    ≈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).

    10.6B128K ctx Llama 3.2 Community License
    7.1KSept 2024
    • Same category
    • Similar size (10.6B vs 10.5B)
    vs
  17. inclusionAI logo

    ZwZ-8B

    inclusionAI·Vision

    ≈6.8 GB

    ZwZ-8B is a fine-grained multimodal perception model built upon Qwen3-VL-8B. It is trained using Region-to-Image Distillation (R2I) combined with reinforcement learning, enabling superior fine-grained visual understanding in a single forward pass — no inference-time zooming or tool calling required.

    8.8B256K ctx Apache 2.0
    517Feb 2026gguf
    • Same category
    • Similar size (8.8B vs 10.5B)
    • Commercial use OK
    vs
  18. huihui-ai logo≈19 GB

    This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

    27.8B256K ctx Apache 2.0
    170.2KAug 2026gguf
    • Same category
    • Larger (27.8B vs 10.5B)
    • Commercial use OK
    vs
  19. OpenMOSS-Team logo

    moss-video-preview-realtime-sft

    OpenMOSS-Team·Vision

    ≈8.1 GB

    We introduce MOSS-Video-Preview-Real-Time-SFT, a specialized model derived from MOSS-Video-Preview-SFT through an additional Real-Time Supervised Fine-Tuning (Real-Time SFT).

    10.7B128K ctx Apache 2.0
    81Mar 2026
    • Same category
    • Similar size (10.7B vs 10.5B)
    • Commercial use OK
    vs
  20. 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
    3.4KOct 2026gguf
    • Same category
    • Similar size (19.4B vs 10.5B)
    • Commercial use OK
    vs
  21. jdopensource logo

    JoyAI-VL-Interaction-Preview

    jdopensource·Vision

    ≈6.8 GB

    The first open, vision-driven real-time interaction model — it watches a live video stream and decides on its own when to speak, stay silent, or delegate.

    8.8B256K ctx Apache 2.0
    160Jun 2026gguf
    • Same category
    • Similar size (8.8B vs 10.5B)
    • Commercial use OK
    vs
  22. openbmb logo

    MiniCPM-V-4.7-35B-A3B

    openbmb·Vision

    ≈22 GB

    GitHub · On-device results · Evaluation · Examples · Usage · Model weights

    35.2BA3B256K ctx Apache 2.0
    875.7KOct 2026gguf
    • Same category
    • Larger (35.2B vs 10.5B)
    • Commercial use OK
    vs
  23. XiaomiMiMo logo

    MiMo-VL-7B-SFT-2508

    XiaomiMiMo·Vision

    ≈6.5 GB

    We're excited to announce improvements to our MiMo-VL (MiMo-VL-7B-RL-2508 and MiMo-VL-7B-SFT-2508), featuring enhanced performance across multiple benchmarks, improved thinking control capabilities, and better user experience.

    8.3B125K ctx MIT
    2.8KAug 2025gguf
    • Same category
    • Similar size (8.3B vs 10.5B)
    • Commercial use OK
    vs
  24. 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
    • Larger (27.4B vs 10.5B)
    • Commercial use OK
    vs