Qwen3.5 REAP 97B A10B 4bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Qwen3.5 REAP 97B A10B 4bit   URL Share it on

Qwen3.5 REAP 97B A10B 4bit is an open-source language model by mlx-community. Features: 97b LLM, VRAM: 54.3GB, License: apache-2.0, Quantized.

  4-bit   4bit Base model:openmose/qwen3.5-re... Base model:quantized:openmose/...   Conversational   Mlx   Moe   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow

Qwen3.5 REAP 97B A10B 4bit Parameters and Internals

LLM NameQwen3.5 REAP 97B A10B 4bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/Qwen3.5-REAP-97B-A10B-4bit 
Base Model(s)  OpenMOSE/Qwen3.5-REAP-97B-A10B   OpenMOSE/Qwen3.5-REAP-97B-A10B
Model Size97b
Required VRAM54.3 GB
Updated2026-04-02
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-11   5.2 GB: 2-of-11   5.2 GB: 3-of-11   5.2 GB: 4-of-11   5.2 GB: 5-of-11   5.2 GB: 6-of-11   5.2 GB: 7-of-11   5.2 GB: 8-of-11   5.2 GB: 9-of-11   5.2 GB: 10-of-11   2.2 GB: 11-of-11
Quantization Type4bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Rank the Qwen3.5 REAP 97B A10B 4bit Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52438 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a