Qwen3-Next-80B-A3B-Instruct-REAP

SamsungSAILMontreal/Qwen3-Next-80B-A3B-Instruct-REAP

Qwen3-Next-80B-A3B-Instruct-REAP is a text generation model from SamsungSAILMontreal. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

Downloads · 30 days

20% of all-time downloads

All-time downloads

182

Public

Parameters

60.3B

121 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors121 GB · 100%

At a glance

Task: Text Generation
Library: transformers
License: apache-2.0
Model type: qwen3_next
Access: Public
Created: Jan 28, 2026
Updated: Jan 28, 2026
SHA: 2c07f5d6

Try a prompt

Base models

Qwen/Qwen3-Next-80B-A3B-Instruct

Model card

From the Hugging Face model README

Qwen3-Next-80B-A3B-Instruct-REAP

This model is a compressed version of Qwen/Qwen3-Next-80B-A3B-Instruct. It is obtained by reducing the number of experts in each MoE layer from 512 to 384 using the REAP baseline method as described in https://bknyaz.github.io/blog/2026/moe/. The compressed model has 60B params (120GB) instead of 80B (160GB) of the original model, reducing storage and GPU memory requirements by roughly 25%. At the same time, the model retains >=94% of the original model's performance on a variety of benchmarks (see Results section below). Additional efficiency optimization (e.g., quantization) can be added similarly to the original model.

See additional details at Qwen3-30B-A3B-Instruct-2507-REAM.

Results

Model	IFeval	AIME25	GSM8K	GPQA-D	HumanEval	LiveCodeBench	AVG
Qwen3-Next-80B-A3B-Instruct	93.4	80.0	78.6	47.0	95.1	43.2	72.9
Qwen3-Next-80B-A3B-Instruct-REAP	91.0	66.7	78.8	37.9	91.5	45.0	68.5

License

Please refer to the license of the original model Qwen/Qwen3-Next-80B-A3B-Instruct.

Task: Text Generation
Library: transformers
Type: qwen3_next
License: apache-2.0
Created: Jan 28, 2026
Updated: Jan 28, 2026