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.
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.
We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance.
7.9B32K ctx Qwen License27.4K 11Apr 2025- Same category
- Similar size (7.9B vs 10.5B)
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 2.0380 52Jan 2026- Same category
- Similar size (10.2B vs 10.5B)
- Commercial use OK
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 2.0449 7Oct 2026- Same category
- Similar size (7.9B vs 10.5B)
- Commercial use OK
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 2.0857 69Mar 2026- Same category
- Similar size (8.7B vs 10.5B)
- Commercial use OK
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 2.05K 17Aug 2025- Same category
- Similar size (8.5B vs 10.5B)
- Commercial use OK
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 2.036.4K 129Oct 2026- Same category
- Smaller (4.8B vs 10.5B)
- Commercial use OK
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 License15.7K 249Apr 2025- Same category
- Similar size (8.3B vs 10.5B)
- Commercial use OK
UI2Code^N: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation
10.3B64K ctx MIT456 27Nov 2025- Same category
- Similar size (10.3B vs 10.5B)
- Commercial use OK
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 MIT3.2K 622Oct 2025- Same category
- Similar size (8.3B vs 10.5B)
- Commercial use OK
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 2.0110 19Jul 2026- Same category
- Similar size (11.3B vs 10.5B)
- Commercial use OK
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-research3.2K 68Apr 2025- Same category
- Similar size (9.8B vs 10.5B)
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 MIT2.6K 77Nov 2025- Same category
- Similar size (8.3B vs 10.5B)
- Commercial use OK
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 MIT5.7K 98Aug 2025- Same category
- Similar size (8.3B vs 10.5B)
- Commercial use OK
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 2.0195 108Apr 2026- Same category
- Similar size (11.3B vs 10.5B)
- Commercial use OK
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 2.02.6K 68Sept 2025- Same category
- Similar size (8.5B vs 10.5B)
- Commercial use OK
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 License7.1K 619Sept 2024- Same category
- Similar size (10.6B vs 10.5B)
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 2.0517 50Feb 2026- Same category
- Similar size (8.8B vs 10.5B)
- Commercial use OK
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 2.0170.2K 819Aug 2026- Same category
- Larger (27.8B vs 10.5B)
- Commercial use OK
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 2.081 30Mar 2026- Same category
- Similar size (10.7B vs 10.5B)
- Commercial use OK
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 2.03.4K 102Oct 2026- Same category
- Similar size (19.4B vs 10.5B)
- Commercial use OK
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 2.0160 93Jun 2026- Same category
- Similar size (8.8B vs 10.5B)
- Commercial use OK
GitHub · On-device results · Evaluation · Examples · Usage · Model weights
35.2BA3B256K ctx Apache 2.0875.7K 1.1KOct 2026- Same category
- Larger (35.2B vs 10.5B)
- Commercial use OK
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 MIT2.8K 37Aug 2025- Same category
- Similar size (8.3B vs 10.5B)
- Commercial use OK
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 2.079.3K 2.4KSept 2026- Same category
- Larger (27.4B vs 10.5B)
- Commercial use OK