← Back to Explorer
Pending

GLM-5.3-Flash (2026)

GLM-5.3-Flash is a large language model released by Zhipu AI (zai-org), released under the MIT license, with a claimed knowledge cutoff of 2026-08-25. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.

Description

Faster/smaller variant of GLM-5.3, part of Zhipu's dense release cadence.

Metadata

Type
LLM
Issuer
Zhipu AI (zai-org)
License
MIT
Size
305.79 GB
Knowledge cutoff
2026-08-25
Source
https://huggingface.co/zai-org/GLM-5.3-Flash
Revision
eb9eb208eb0d988989d07a6a12d0fdeb5f52574a

Hugging Face stats

4,242,609 downloads on Hugging Face · 2,568 likes · pipeline: image-text-to-text · library: transformers

transformerssafetensorsglm5_nextimage-text-to-textconversationalenzheval-resultsendpoints_compatiblefp8

Weight Hashes

Weights file
62 shards (Merkle root) · 305.79 GB
SHA-2568f80d6d5bde942926da6e0e34bd56084394394f4d8f2e7969aa0b3c977a56e52
SHA3-2568cf09323e0e5235b627745ffca844fd56c5cc95a2a3b8b7ae16dfa6c94175577
BLAKE3a6e9c4057606546efe17aebd9b4f853668d1492d39f02e713b678e4206c622b8
Config file
config.json · 67.79 KB
SHA-256bb8f01c42cb92a52ca72e65afb4d5bd8d11aef083cd210e8de25dfb904f23e9f
SHA3-256adce58eb09c35defce68ec53f9a4f58de207d343bc4fcc83a05a697a5e7b90fd
BLAKE39be2ac5c43955c8d8621fdb1aa6dcd99b5a74f9ba42dac73c0a3599a3afd0fb3
Tokenizer file
tokenizer.json · 19.28 MB
SHA-25619e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
SHA3-256a3539041a2669ebeacaeac71a0b34dcc38f54933f78d7c3c8c7634a483bbabf3
BLAKE395875d64ad7f0287b7c4c3ac262475aff876301b4d71c31a939496f92d0a4836

Verify it yourself

Download the file(s) from the source below, then hash them locally (sha256sum <file> on Linux/macOS, certutil -hashfile <file> SHA256 on Windows) and compare the output against the hash(es) shown above.