Ling-3.0-flash is a large language model released by InclusionAI (Ant Group), released under the mit license, with a claimed knowledge cutoff of 2026-07-23. Its weights, configuration, and tokenizer files could not be hashed successfully -- see the error below by Weight Registry.
Description
Ling-3.0-flash is a 124B-parameter Mixture-of-Experts model from Ant Group's InclusionAI lab, open-sourced August 5, 2026 under MIT license with only 5.1B parameters activated per token (~1/64 expert activation). Ant Group reports it matches or beats the company's own 1-trillion-parameter Ring-2.6 flagship on 11 of 12 benchmarks despite the far smaller active footprint, and it supports a 256K-token context for coding, search, and agent tasks.
Metadata
Hugging Face stats
16,573 downloads on Hugging Face · 418 likes · pipeline: text-generation
Weight Hashes
Hashing failed -- see the note below for the error.
Error
('Connection broken: IncompleteRead(5097072986 bytes read, 5618353926 more expected)', IncompleteRead(5097072986 bytes read, 5618353926 more expected))