← Back to Explorer
Pending

Qwen3-235B-A22B-Thinking-2507 (2025)

Qwen3-235B-A22B-Thinking-2507 is a large language model released by Alibaba, released under the apache-2.0 license, with a claimed knowledge cutoff of 2025-06-30. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.

Description

Qwen3-235B-A22B-Thinking-2507 is a high-performance open-weight Mixture-of-Experts model from Alibaba's Qwen3 line, released July 2025, activating 22B of its 235B parameters per forward pass and optimized for complex reasoning tasks with native support for up to 262,144-token context.

Metadata

Type
LLM
Issuer
Alibaba
License
apache-2.0
Size
437.90 GB
Knowledge cutoff
2025-06-30
Source
https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507
Revision
6cbffae6d8e28b986a6b17bd36f42f9fa0f1f0a5

Hugging Face stats

15,638 downloads on Hugging Face · 410 likes · pipeline: text-generation · library: transformers

transformerssafetensorsqwen3_moetext-generationconversationaleval-resultsendpoints_compatible

Weight Hashes

Weights file
118 shards (Merkle root) · 437.90 GB
SHA-25683a78406ebbd4053d67f9f7f67f6528f5eb669a2508d6ef2fcb2ef99c8ffb65c
SHA3-2569d3c1600e84af443659f40cbcea9855be26274d59f6c319d577b78332aa86739
BLAKE3872e8f6c893988131c73c600962bf74e530b1bac3cb93cd7f4470c13c51ea275
Config file
config.json · 964 B
SHA-256ad59a339665ee1c68cbff06ac72c9e59f5183ebfaf3698c98737e003a870e9e2
SHA3-2561619940dd47c051a53b1a997afbf21b47971f214fdc6208c994f574bf4f27043
BLAKE3e7afab107c73f891b0e0de7c9a1d07b6ad2265055e22eefb379c33f17d69b862
Tokenizer file
tokenizer.json · 6.71 MB
SHA-25619564a48c4f71a2a1b937cce34c737a1e662b171c5f5d7edf641a15cd896f07d
SHA3-25670973ae99c5f79e916cbdf154df223c8d557cab98a771823c10e4783deba2950
BLAKE3e4bf149b34e0372424d0cd7afba11bbda682d8a3bb29b95a02a7c97e89dc63a2

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.