Agnes 2.5 Pro Theta is a multimodal mixture-of-experts checkpoint distributed with its model implementation, tokenizer, chat template, and image/video processors. This release provides BF16 weights for local inference through Transformers.
Alternatives to Agnes-2.5-Pro-Theta
120 open-weight models that do the same job as Agnes-2.5-Pro-Theta (188B 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.
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 licence525.4K 136Jun 2026- Same category
- Smaller (903M vs 188B)
- Commercial use OK
We introduce Intern-S2-Mobius, a 35B foundation model built on the Mobius-v0 architecture realized by Xtuner and LMDeploy.
36B256K ctx Apache 2.01.1K 66Jul 2026- Same category
- Smaller (36B vs 188B)
- Commercial use OK
We introduce Intern-S2-Preview, an efficient 35B scientific multimodal foundation model. Beyond conventional parameter and data scaling, Intern-S2-Preview explores task scaling: increasing the difficulty, diversity, and coverage of scientific tasks to further unlock model capabilities.
36.1BA4.9B256K ctx Apache 2.01.7K 123May 2026- Same category
- Smaller (36.1B vs 188B)
- Commercial use OK
One Gateway. Every Model. — Route Smarter · Ship Safer · Spend Less.
27.8BApache 2.08.3K 542Aug 2026- Same category
- Smaller (27.8B vs 188B)
- Commercial use OK
For NEO Imatrix GGUFS - reg and MTP, as well as full model details/card please go here:
40B256K ctx Apache 2.0345 68Jul 2026- Same category
- Smaller (40B vs 188B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
4.4B256K ctx Apache 2.03M 543Oct 2025- Same category
- Smaller (4.4B vs 188B)
- Commercial use OK
- Widely used
Flora-rewarder-27B produces outcome rewards (an episode-level success score), used for monitoring real-world deployments, and process rewards (dense action-quality scores over short time steps), used during reinforcement learning-based post-training.
27.8B256K ctx NVIDIA Non-Commercial License5.5K 23Oct 2026- Same category
- Smaller (27.8B vs 188B)
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
873M256K ctx Apache 2.0872.1K 141Feb 2026- Same category
- Smaller (873M vs 188B)
- Commercial use OK
Flora-captioner-27B generates one action instruction for a supplied target interval in a robot or human manipulation video. It uses neighboring video context to disambiguate the intended local operation.
27.4B256K ctx NVIDIA Non-Commercial License5.6K 44Oct 2026- Same category
- Smaller (27.4B vs 188B)
HyperCLOVA X SEED 32B Think is an updated vision-language thinking model that advances the SEED Think 14B line beyond simple scaling, pairing a unified vision-language Transformer backbone with a reasoning-centric training recipe.
33.3B128K ctx hyperclovax7K 408Dec 2025- Same category
- Smaller (33.3B vs 188B)
NVIDIA-Ising-Calibration-1 analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis question categories. NVIDIA-Ising-Calibration-1 was developed by NVIDIA as a quantum calibration vision-language model built on Qwen3.5-35B-A3B.
35BA3B256K ctx NVIDIA Open Model License1.9K 62Mar 2026- Same category
- Smaller (35B vs 188B)
- Commercial use OK
AREX-2 is a 27B-parameter long-horizon agent model from the Beijing Academy of Artificial Intelligence (BAAI). It learns to improve a solution over multiple test-time rounds: propose, measure, reflect, and revise.
27.4B256K ctx Apache 2.03.8K 218Sept 2026- Same category
- Smaller (27.4B vs 188B)
- 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.
38.4B40K ctx Apache 2.03.7K 47Aug 2025- Same category
- Smaller (38.4B vs 188B)
- Commercial use OK
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
27.4B128K ctx Gemma Terms of Use291K 2.1KMar 2025- Same category
- Smaller (27.4B vs 188B)
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).
88.6B128K ctx Llama 3.2 Community License22 136Sept 2024- Same category
- Smaller (88.6B vs 188B)
🔥 Update (April 5): I’ve released the complete training notebook, codebase, and a comprehensive PDF guide to help beginners and enthusiasts understand and reproduce this model's fine-tuning process.
27.8B256K ctx Apache 2.014.2K 3KFeb 2026- Same category
- Smaller (27.8B vs 188B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
4.7B256K ctx Apache 2.0504K 133Feb 2026- Same category
- Smaller (4.7B vs 188B)
- 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 2.0337.9K 43Apr 2026- Same category
- Smaller (9.7B vs 188B)
- Commercial use OK
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 2.0129.6K 83Aug 2026- Same category
- Smaller (2.6B vs 188B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
2.1B256K ctx Apache 2.01.1M 521Oct 2025- Same category
- Smaller (2.1B vs 188B)
- Commercial use OK
GLiDE is a decision model from Fastino. Given a state (text or JSON, optionally with images) and one or more typed questions, it returns a probability for every option of every question. Internal use only.
26.1B256K ctx fastino-community3.6K 103Oct 2026- Same category
- Smaller (26.1B vs 188B)
H2O-Lightning-31B is a 31B-parameter decision model from H2O.ai, built on google/gemma-4-31B-it. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation), and about images that come with the record. It returns a probability for every option:
31.3Bh2o-model-non-commercial-licence-v1.1690 8Oct 2026- Same category
- Smaller (31.3B vs 188B)
Inference provider: Fastino — use GLiDE through Fastino's hosted API (POST https://api.fastino.ai/v1/systemone, model fastino/GLiDE). Get an API key · API documentation
26.1B256K ctx fastino-community3.6K 103Oct 2026- Same category
- Smaller (26.1B vs 188B)
This repository contains an earlier open-weight Preview checkpoint of Agnes 3.0 Flash. It is distinct from the newer production/API checkpoint listed on Artificial Analysis. The Preview release has 33B parameters and a context window of 262,144 tokens.
33.1B256K ctx Apache 2.0485 250Sept 2026- Same category
- Smaller (33.1B vs 188B)
- Commercial use OK