← Back to Explorer
Shortlisted

Qwen3.8-2.4T-A95B (2026)

Qwen3.8-2.4T-A95B is a large language model released by Alibaba, released under the Apache-2.0 license, with a claimed knowledge cutoff of 2026-08-12. Its weights, configuration, and tokenizer files are shortlisted for hashing and on-chain attestation by Weight Registry.

Description

Very large Qwen3.8-generation MoE model.

Metadata

Type
LLM
Issuer
Alibaba
License
Apache-2.0
Size
—
Knowledge cutoff
2026-08-12
Source
https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B
Revision
—

Hugging Face stats

53,100 downloads on Hugging Face · 1,261 likes · pipeline: text-generation · library: transformers

transformerssafetensorsqwen3_5_moe_texttext-generationconversationaleval-resultsendpoints_compatible

Weight Hashes

Not yet hashed -- queued for processing.