Nex-N2.6 is a multimodal agentic model from Nex-AGI, built on GLM-5.3-Flash. It is designed for computer use, coding, and long-horizon tasks involving tools. This repository contains the FP8-quantized weights of Nex-N2.6, with approximately 321B parameters.
Alternatives to Nex-N2.6
120 open-weight models that do the same job as Nex-N2.6 (321B 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.
MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference.
1.6B256K ctx Apache 2.0468.8K 418Oct 2026- Same category
- Smaller (1.6B vs 321B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
873M256K ctx Apache 2.02.5M 856Feb 2026- Same category
- Smaller (873M vs 321B)
- Commercial use OK
- Widely used
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
8.8B256K ctx Apache 2.06.1M 1.3KOct 2025- Same category
- Smaller (8.8B vs 321B)
- Commercial use OK
- Widely used
Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series.
2.78T1M ctx kimi-k3.1-pro68K 2.4KNov 2026- Same category
- Larger (2.78T vs 321B)
NVIDIA Nemotron Parse 2.0 transforms document images into structured, machine-readable representations with text, layout classes, bounding boxes, and reading-order information.
903M9K ctx Custom licence650.6K 136Jun 2026- Same category
- Smaller (903M vs 321B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
27.8B256K ctx Apache 2.01.6M 1.1KFeb 2026- Same category
- Smaller (27.8B vs 321B)
- Commercial use OK
DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.
25.8BA4B256K ctx Apache 2.0563.7K 1.3KJun 2026- Same category
- Smaller (25.8B vs 321B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
4.4B256K ctx Apache 2.02.8M 544Oct 2025- Same category
- Smaller (4.4B vs 321B)
- Commercial use OK
- Widely used
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
873M256K ctx Apache 2.0880.7K 142Feb 2026- Same category
- Smaller (873M vs 321B)
- 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
- Smaller (27.8B vs 321B)
- Commercial use OK
This family of models performs vision-language and text-only tasks including optical character recognition, multimodal reasoning, localization, common sense reasoning, world knowledge utilization, and coding.
79.4B32K ctx CC BY-NC 4.07.9K 780Sept 2024- Same category
- Smaller (79.4B vs 321B)
Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware.
29.8B128K ctx Apache 2.0149.3K 2.2KAug 2026- Same category
- Smaller (29.8B vs 321B)
- Commercial use OK
We're excited to unveil Qwen2-VL, the latest iteration of our Qwen-VL model, representing nearly a year of innovation.
73.4B32K ctx Qwen License14.9K 318Sept 2024- Same category
- Smaller (73.4B vs 321B)
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
4.7B256K ctx Apache 2.0496.7K 133Feb 2026- Same category
- Smaller (4.7B vs 321B)
- Commercial use OK
ZAYA1-VL-8B is a vision-language model (VLM) built upon Zyphra's ZAYA1-8B LLM. It has state-of-the-art performance among VLMs for its size and inference efficiency.
9.7B32K ctx Apache 2.0339.4K 43Apr 2026- Same category
- Smaller (9.7B vs 321B)
- 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
- Smaller (27.4B vs 321B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
2.1B256K ctx Apache 2.01.2M 522Oct 2025- Same category
- Smaller (2.1B vs 321B)
- Commercial use OK
Interfaze 1.1 Lite is a mixture-of-architectures (MoA) model for developer workloads: reading documents, transcribing speech, locating objects and interface elements, and answering over all of it with structured output.
?Binterfaze-open133 69Oct 2026- Same category
Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware.
2.6B128K ctx Apache 2.090.3K 83Aug 2026- Same category
- Smaller (2.6B vs 321B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
2.3B256K ctx Apache 2.0321.5K 108Feb 2026- Same category
- Smaller (2.3B vs 321B)
- Commercial use OK
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
1.3B256K ctx Apache 2.0194.5K 1.3KApr 2026- Same category
- Smaller (1.3B vs 321B)
- Commercial use OK
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.
73.4B32K ctx Apache 2.02.9K 159Jan 2025- Same category
- Smaller (73.4B vs 321B)
- Commercial use OK
NVIDIA Cosmos Reason 2 is an open, customizable, 2B-parameter reasoning vision language model (VLM) for physical AI and robotics that 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.
2.4B256K ctx NVIDIA Open Model License475.6K 420Dec 2025- Same category
- Smaller (2.4B vs 321B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
9.7B256K ctx Apache 2.0266.8K 163Feb 2026- Same category
- Smaller (9.7B vs 321B)
- Commercial use OK