Atria Dawn Preview

Name: Atria Dawn Preview
Author: Shanghai AI Laboratory

Shanghai AI LaboratoryOpen WeightsPending Human Review

Atria Dawn Preview is Shanghai AI Laboratory’s agentic model for turning research and engineering questions into executable results. Built on GLM-5.2’s 744B mixture-of-experts foundation, it is post-trained for discovery, code creation, office deliverables, and cybersecurity tasks in authorized environments. The released text-only checkpoint supports a documented 256K inference context, downloadable MIT-licensed weights, and hosted API access. It combines tool execution with environmental feedback for experiment design, failure recovery, and verification. Configuration maximums above the documented serving limit are not treated as evidence of a larger supported context.

2026-09-14

744B

Mixture-of-Experts Transformer with sparse attention

MIT

Compare with other models

Specifications

Parameters: 744B
Architecture: Mixture-of-Experts Transformer with sparse attention
License: MIT
Context Window: 256,000 tokens
Type: text
Modalities: text

Benchmark Scores

Advanced Specifications

Model Family: Atria
Finetuned From: GLM-5.2
API Access: Available
Chat Interface: Not Available
Variants: Atria-Dawn-PreviewAtria-Dawn-Preview-FP8

Capabilities & Limitations

Capabilities: agentic reasoningcodingtool useresearchlong context
Known Limitations: Text-only checkpoint; image inputs are unsupportedPreview behavior can changeFull weights require distributed serving
Notable Use Cases: scientific experiment automationengineering agentsdocument deliverables
Function Calling Support: Yes
Tool Use Support: Yes

Resources

Related Models

Intern S2 397B

Shanghai AI Laboratory

Intern S2 is the stable scientific multimodal follow-up to the 397B preview checkpoint. It strengthens extended agent execution and research workflows, with deep-thinking and ordinary-response modes. Public API documentation identifies the stable model separately and schedules preview decommissioning for October 31. The release includes downloadable Apache-licensed weights and chat access. The official laboratory announcement identifies the public release date as 2026-09-13.

Intern Lumina U2

Shanghai AI Laboratory

Intern Lumina U2 is a unified language-capable multimodal diffusion model covering text questions, visual understanding, image generation, and editing. Its sparse 16B backbone activates 1B parameters and uses an eight-codebook discrete visual tokenizer. The Ascend-trained weights are publicly available; the NVIDIA-trained checkpoint, training code, and report remain future work. Code publication in August preceded the September weight release. Primary catalogs verify the release month; the exact first-public day remains unverified and is not inferred from private repository or API creation metadata.

Typemultimodal

Parameters16B total, 1B active

2026-09

Open Weights

Details Compare

Intern S2 Mobius

Shanghai AI Laboratory

Intern S2 Mobius is a 35B research model that separates knowledge storage from reasoning computation. Globally shared memory lets recurrent reasoners refine continuous hidden states and access knowledge beyond a fixed layer hierarchy. It is continually pretrained from Qwen3.5-35B and post-trained with supervised learning and reinforcement learning. The public checkpoint and deployment code allow study of concise latent reasoning and multi-token prediction. Primary catalogs verify the release month; the exact first-public day remains unverified and is not inferred from private repository or API creation metadata.