This repository provides a reproduction checkpoint of Axion 1.0-35B, following the recipe described in Axion 1.0: Open Agent Foundation Models, Simplified. The model is designed for scientific reasoning, information seeking, and tool-augmented problem solving.
Alternatives to Axion-1.0-35B
120 open-weight models that do the same job as Axion-1.0-35B (35.1B chat), 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.
Phi-3.5-MoE is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available documents - with a focus on very high-quality, reasoning dense data. The model supports multilingual and comes with 128K context length (in tokens).
41.9BA6.6B128K ctx MIT20.8K 590Aug 2024- Same category
- Similar size (41.9B vs 35.1B)
- Commercial use OK
We release Nomos 1, a specialization of Qwen/Qwen3-30B-A3B-Thinking-2507 for mathematical problem-solving and proof-writing in natural language. Nomos-1 was trained in collaboration with Hillclimb AI.
30.5BA3.4B256K ctx Apache 2.0409 159Dec 2025- Same category
- Similar size (30.5B vs 35.1B)
- Commercial use OK
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
34.4B32K ctx Apache 2.09.7K 37May 2024- Same category
- Similar size (34.4B vs 35.1B)
- Commercial use OK
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
34.4B16K ctx Apache 2.09.6K 27May 2024- Same category
- Similar size (34.4B vs 35.1B)
- Commercial use OK
This model was presented in the paper WebDancer: Towards Autonomous Information Seeking Agency.
32.8B40K ctx MIT701 57Jun 2025- Same category
- Similar size (32.8B vs 35.1B)
- Commercial use OK
The GLM family welcomes new members, the GLM-4-32B-0414 series models, featuring 32 billion parameters. Its performance is comparable to OpenAI’s GPT series and DeepSeek’s V3/R1 series. It also supports very user-friendly local deployment features.
32.6B32K ctx MIT1.1K 38Apr 2025- Same category
- Similar size (32.6B vs 35.1B)
- Commercial use OK
The Yi series models adopt the same model architecture as Llama but are NOT derivatives of Llama.
34.4B4K ctx Apache 2.028.5K 358Nov 2023- Same category
- Similar size (34.4B vs 35.1B)
- Commercial use OK
Today we introduce Maple-Preview, an open-source 20B-A1B ternary-weight reasoning LLM. Maple-Preview has SOTA reasoning for its weight class and is even competitive with larger models.
20.2BA1.5B128K ctx MIT2K 434Aug 2026- Same category
- Similar size (20.2B vs 35.1B)
- Commercial use OK
Aya Expanse 32B is an open-weight research release of a model with highly advanced multilingual capabilities. It focuses on pairing a highly performant pre-trained Command family of models with the result of a year’s dedicated research from Cohere Labs, including data arbitrage, multilingual…
32.3BCC BY-NC 4.03.5K 303Oct 2024- Same category
- Similar size (32.3B vs 35.1B)
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
21.9BA3B128K ctx Apache 2.016.6K 178Jun 2025- Same category
- Similar size (21.9B vs 35.1B)
- Commercial use OK
BrowseSafe is a multi-layered defense strategy comprising both architectural and model-based defenses to protect against evolving prompt injection attacks. It is a specialized security model designed to protect AI browser agents from prompt injection attacks embedded in real-world web content.
30.5BA3.4B256K ctx MIT277 53Nov 2025- Same category
- Similar size (30.5B vs 35.1B)
- Commercial use OK
This is the model card for EuroLLM-22B. You can also check the post-trained version: EuroLLM-22B-Instruct-2515.
22.6B32K ctx Apache 2.04.1K 22Nov 2025- Same category
- Similar size (22.6B vs 35.1B)
- Commercial use OK
Dolphin Mistral 24B Venice Edition is a collaborative project we undertook with Venice.ai with the goal of creating the most uncensored version of Mistral 24B for use within the Venice ecosystem.
24B128K ctx Apache 2.07.4K 790Jun 2025- Same category
- Similar size (24B vs 35.1B)
- Commercial use OK
🤗 Models    |    📑 Paper    |    🔗 Github   
32.9BA5.8B40K ctx Apache 2.0248 45Aug 2025- Same category
- Similar size (32.9B vs 35.1B)
- Commercial use OK
(a) On MMLU-Pro (4k context length), Kimi Linear achieves 51.0 performance with similar speed as full attention. On RULER (128k context length), it shows Pareto-optimal performance (84.3) and 3.98x speedup.
49.1BA3B1M ctx MIT1.8K 85Oct 2025- Same category
- Similar size (49.1B vs 35.1B)
- Commercial use OK
The Cogito LLMs are instruction tuned generative models (text in/text out). All models are released under an open license for commercial use.
32.8B128K ctx Apache 2.0709 117Mar 2025- Same category
- Similar size (32.8B vs 35.1B)
- Commercial use OK
Jamba2 Mini is an open source small language model built for enterprise reliability. With 12B active parameters (52B total), it delivers precise question answering without the computational overhead of reasoning models.
51.6B256K ctx Apache 2.01.3K 58Jan 2026- Same category
- Similar size (51.6B vs 35.1B)
- Commercial use OK
Large Action Models (LAMs) are advanced language models designed to enhance decision-making by translating user intentions into executable actions.
32.8B32K ctx CC BY-NC 4.0654 35Mar 2025- Same category
- Similar size (32.8B vs 35.1B)
🚀 LLaDA2.1-flash is now live on ZenmuxAI! Try it via API 🛠️ or Chat 💬: https://zenmux.ai/inclusionai/llada2.1-flash
16.3BA1.4B32K ctx Apache 2.028.2K 128Feb 2026- Same category
- Smaller (16.3B vs 35.1B)
- Commercial use OK
Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work.
118BA6.1B1M ctx Custom licence488.2K 1.1KJul 2026- Same category
- Larger (118B vs 35.1B)
- 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.
27.2B8K ctx Gemma Terms of Use23.2K 579Jun 2024- Same category
- Similar size (27.2B vs 35.1B)
Chirp Chirp! 🐦 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast Stronger. Faster. Leaner. It delivers stronger benchmark results, finishes tasks faster, and produces shorter outputs, bringing better instruction following, stronger task decomposition, and deeper knowledge of real-world…
125BA12.7B256K ctx MIT341.7K 227Oct 2026- Same category
- Larger (125B vs 35.1B)
- Commercial use OK
ALIA-40b is a highly multilingual model pre-trained from scratch that will come with its respective base and instruction-tuned variants. This model card corresponds to the 40b base version.
40.4B32K ctx Apache 2.02.1K 89Dec 2024- Same category
- Similar size (40.4B vs 35.1B)
- Commercial use OK
The Meta Llama 3.3 multilingual large language model (LLM) is an instruction tuned generative model in 70B (text in/text out).
70.6B128K ctx Llama 3.3 Community License344.9K 3.2KNov 2024- Same category
- Larger (70.6B vs 35.1B)