Best open-source multimodal models in 2026 (images, video and audio)

Most of the new open flagships on this site read images, and many also take video or audio. This list picks the open models where that is a main feature, from phone-sized to server-sized, and shows which licenses let you ship them.

  • List updated November 11, 2026
  1. Gemma 4

    Google's Apache 2.0 family, from phone-sized E2B to a 31B flagship. It takes text, images, video and audio, and has reasoning and tool use.

    • Google DeepMind
    • 30.7B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 3.52 GB
  2. Qwen3.8-27B

    A 27B dense Apache 2.0 model that reads images and video, reasons step by step and fits on one GPU.

    • Alibaba Qwen
    • 27.8B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 19 GB
  3. Qwen3.6

    Alibaba's Apache 2.0 Qwen3.6 pair, a 35B mixture of experts with 3B active and a 27B dense model, both with image and video input and tuned for agentic coding.

    • Alibaba Qwen
    • 36B (3B active)
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 19 GB
  4. Qwen3.5

    Alibaba's Apache 2.0 family from 0.8B to 397B, with image and video input, 201 languages and a 256K context.

    • Alibaba Qwen
    • 403B (17B active)
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 0.602 GB
  5. MiniCPM-V 4.7

    OpenBMB's Apache 2.0 phone-friendly models: a 35B-A3B mixture of experts and a 1B model, both with images and video.

    • OpenBMB
    • 35.2B (3B active)
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 1.07 GB
  6. MiniCPM-o 4.5

    OpenBMB's 9B Apache 2.0 model that sees, listens and speaks at once. It takes video and audio live while it answers in text and English or Chinese speech, and OpenBMB lists 11 GB of GPU memory at int4.

    • OpenBMB
    • 9.37B
    • 40K tokens
    • Apache 2.0 (Permissive)
    • from 11 GB
  7. Mage-VL

    Microsoft's 4B Apache 2.0 vision-language model that reads video like a codec, cutting visual tokens by more than 75%, with a gate for live streams. Microsoft's tables put it ahead of Qwen3-VL-4B on most video and spatial tests.

    • Microsoft
    • 4.74B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 3.27 GB
  8. LocateAnything-3B

    NVIDIA's 3B model that answers with boxes and points for objects, GUI elements and text, at 12.7 boxes per second on an H100 by NVIDIA's measure. The license is research only.

    • NVIDIA
    • 3.83B
    • NVIDIA Non-Commercial (Non-commercial)
    • from 2.64 GB
  9. Ternary Bonsai 2

    PrismML's vision-language models with ternary weights, from a 2B model in 0.43 GB to a 27B-class model in 5.95 GB, under Apache 2.0. They take images and text.

    • PrismML
    • 27.4B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 0.473 GB
  10. SenseNova-Loop-9B-Preview

    SenseTime's 9B looped vision-language preview under Apache 2.0: layers 4 to 27 run twice, with text and image input and a 256K context. It needs custom code, and its published scores are mixed against Qwen3.5-27B.

    • SenseTime
    • 9.66B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 22 GB
  11. Muse Glimmer

    Meta's 30B dense multimodal model for local agents, distilled from Muse Spark under Apache 2.0 and quantized to fit a 24 GB GPU.

    • Meta
    • 29.6B
    • 128K tokens
    • Apache 2.0 (Permissive)
    • from 20 GB
  12. GLM-5.3-Flash

    The MIT-licensed multimodal GLM: 320B total and 18B active, images and video in, a 1M context, built for cheap long-context serving.

    • Z.ai (Zhipu AI)
    • 320B (18B active)
    • 1M tokens
    • MIT (Permissive)
    • from 221 GB
  13. Step 3.7 Flash

    StepFun's 198B vision-language mixture of experts under Apache 2.0, with 11B active parameters, a 256K context and a 1.8B vision encoder. It targets agents that read screenshots, charts and documents, and a 111.5 GB GGUF fits a 128 GB Mac or mini PC.

    • StepFun
    • 201B (11B active)
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 120 GB
  14. Step 5 Preview

    StepFun's 600B mixture of experts with a 1M context and image input, for agents that analyze long reports, charts and screenshots. The model card also mentions video, but its specification lists only text and image, and the custom license has hardware and hosting terms.

    • StepFun
    • 604B (27B active)
    • 1M tokens
    • StepFun 1.0 (Conditional)
    • from 417 GB
  15. MiMo-V2.6

    Xiaomi's omnimodal agent models: a 1T Pro, a 310B Flash and a 9B research checkpoint, with a 1M context. The license is tagged MIT.

    • Xiaomi
    • 1.02T (42B active)
    • 1M tokens
    • MIT (Permissive)
    • from 6.49 GB
  16. Nemotron 3 Nano Omni

    NVIDIA's 31B mixture of experts with 3B active that takes video, audio, images and text with a 256K context. It's English only, answers in text and runs on one 32 GB RTX 5090 in NVFP4.

    • NVIDIA
    • 31B (3B active)
    • 256K tokens
    • NVIDIA Open Model (Permissive)
    • from 32 GB
  17. Qwen3-Omni

    Alibaba's 30B mixture of experts with 3B active that reads text, images, audio and video and can answer in text or speech in 10 languages. Apache 2.0, but Alibaba lists about 79 GB in BF16 for a 15-second clip.

    • Alibaba Qwen
    • 35.3B (3B active)
    • 64K tokens
    • Apache 2.0 (Permissive)
    • from 22 GB
  18. Muse Spark Open

    Meta's 816B mixture of experts with 42B active and a 1M context, taking text, image, video and audio. It uses Meta's own Muse license, so read it before commercial use.

    • Meta
    • 816B (42B active)
    • 1M tokens
    • Muse Model License (Conditional)
    • from 563 GB
  19. Apertus 1.5

    Swiss AI's fully open 8B and 70B models under Apache 2.0, which read images and audio as well as text with a 262K context. They answer in text only, and the audio understanding is experimental.

    • Swiss AI Initiative
    • 70B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 5.52 GB
  20. LongCat-2.5 Newest

    Meituan's MIT-licensed 1.6T mixture of experts with 48B active parameters, taking text, images and video with a 1M-token context. Deployment is documented only for NPU servers.

    • Meituan
    • 1.6T (48B active)
    • 1M tokens
    • MIT (Permissive)
    • from 1.1 TB
  21. LFM3

    Liquid AI's family has a 1.7B text model with a 256K context that fits in 1 GB, plus vision, audio and omni siblings. The LFM Open License allows commercial use only below US$10 million in yearly revenue.

    • Liquid AI
    • 2.17B
    • 256K tokens
    • LFM Open 1.0 (Conditional)
    • from 1.19 GB
  22. Mirage

    Cactus Compute's 51M Apache 2.0 vision model in a 22 MB file: it describes a photo, finds objects, reads text and fills forms, in 74 ms on a Galaxy S26 NPU. It is not a chat model, and its launch post gives no standard accuracy benchmarks.

    • Cactus Compute
    • 51M
    • Apache 2.0 (Permissive)
    • from 0.0354 GB

How we chose

  • Models that accept images, video or audio as input, with open weights you can download today.
  • Current releases only, so models replaced by a newer generation, such as Qwen3-VL, are left out.
  • Vision benchmark scores come from the developers, so we do not rank on them. Try your own images, because screenshots, charts and handwriting behave very differently from photos.
  • Context length and license are shown because they limit what you can ship.