Qwen3.8-2.4T-A95B

Name: Qwen3.8-2.4T-A95B
Author: Hugging Face

other2446B / 48B

> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with vLLM, SGLang, TokenSpeed, etc.

Context

262K

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Fine-tuning

Details

Model IDQwen/Qwen3.8-2.4T-A95B

ProviderHugging Face

CreatorQwen

Family—

Licenseother

Status—

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters2446B / 48B

Architecturemoe

Context window262K tokens

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2026-08-08

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

API

GET/v1/models/huggingface/Qwen/Qwen3.8-2.4T-A95B