35B Mixture-of-Experts open-weights model from InternScience for long-horizon agentic search, engineering and tool use.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Agents-A1 is a 35B-parameter Mixture-of-Experts language model from the InternScience team, aimed at agentic workflows: long-horizon search, engineering tasks, scientific research, instruction following and tool calling. It is designed to plan, call tools, inspect intermediate state and keep constraints intact over long contexts.
Training uses a domain-grounded knowledge-action graph that turns agent process traces into training targets, followed by three stages: full-domain supervised fine-tuning, domain-level teacher models, and multi-teacher on-policy distillation. The project site reports evaluations across search, engineering, scientific, instruction-following and general agentic benchmarks. A YouTube creator reports it beating Kimi K2.6 and DeepSeek V4 Pro on several benchmarks. That claim has not been independently verified here.
The weights are published on Hugging Face (about 70GB, with FP8 and Q4 variants reported by a creator). The model can be served with SGLang or vLLM through OpenAI-compatible endpoints, with a 262,144-token context setting and Qwen3-style reasoning and tool-call parsers in the example commands. The license was not stated in the provided material.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Open-source 35B MoE model built for agentic workflows that beats Kimi K2.6 and DeepSeek V4 Pro on several benchmarks, and Qwen 35B among local models. Weights are 70GB, with FP8 and Q4 versions available.
Closest neighbours by meaning, not just by category.
Model · Alpha Innovator
35B mixture-of-experts open-weights agentic model for engineering, long-horizon search and scientific research.
Model
Open-weights 35B-A3B agentic model post-trained from Qwen3.6-35B-A3B for search, coding and scientific research.
Model · Meituan
Meituan's open-weights 1.6T-parameter mixture-of-experts LLM (48B active), aimed at agentic coding and reasoning tasks.
Model · Accio Lab
Open-weights 35B MoE (3B active) agentic model from Accio Lab, post-trained from Qwen3.6-35B-A3B.
Model · IQuest Lab
320B-parameter MoE model (15B active) from IQuest for agentic coding and tool use, with 512K context.
Model · Z.ai
Z.ai's open-weights 753B MoE language model, a post-trained GLM-5.2 aimed at coding, agentic tasks and cybersecurity.