LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3.5 REAP 97B A10B by OpenMOSE

 »  All LLMs  »  OpenMOSE  »  Qwen3.5 REAP 97B A10B   URL Share it on

  26   

Qwen3.5 REAP 97B A10B is an open-source language model by OpenMOSE. Features: 122b LLM, VRAM: 194.2GB, License: apache-2.0, LLM Explorer Score: 0.25.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-122b-a...   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/OpenMOSE/Qwen3.5-REAP-97B-A10B 

Qwen3.5 REAP 97B A10B Benchmarks

LLME Score: 0.24706
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3.5 REAP 97B A10B (OpenMOSE/Qwen3.5-REAP-97B-A10B)
🌟 Advertise your project 🚀

Qwen3.5 REAP 97B A10B Parameters and Internals

LLM NameQwen3.5 REAP 97B A10B
Repository 🤗https://huggingface.co/OpenMOSE/Qwen3.5-REAP-97B-A10B 
Base Model(s)  Qwen/Qwen3.5-122B-A10B   Qwen/Qwen3.5-122B-A10B
Model Size122b
Required VRAM194.2 GB
Updated2026-06-02
MaintainerOpenMOSE
Model Typeqwen3_5_moe
Model Files  8.5 GB: 1-of-20   10.6 GB: 2-of-20   9.2 GB: 3-of-20   10.6 GB: 4-of-20   9.0 GB: 5-of-20   10.7 GB: 6-of-20   9.1 GB: 7-of-20   10.7 GB: 8-of-20   9.3 GB: 9-of-20   10.6 GB: 10-of-20   9.2 GB: 11-of-20   10.5 GB: 12-of-20   9.4 GB: 13-of-20   10.6 GB: 14-of-20   9.2 GB: 15-of-20   10.6 GB: 16-of-20   9.2 GB: 17-of-20   10.6 GB: 18-of-20   9.2 GB: 19-of-20   7.4 GB: 20-of-20
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Quantized Models of the Qwen3.5 REAP 97B A10B

Model
Likes
Downloads
VRAM
Qwen3.5 REAP 97B A10B 4bit313954 GB

Best Alternatives to Qwen3.5 REAP 97B A10B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 122B A10B NVFP40K / 83.5 GB125
Qwen3.5 122B A10B Abliterated0K / 248.6 GB645
...3.5 122B A10B GameDev MLX 4bit0K / 44.4 GB23934
...22B A10B Vision MLX Mixed 4bit0K / 4.7 GB1370
Note: green Score (e.g. "73.2") means that the model is better than OpenMOSE/Qwen3.5-REAP-97B-A10B.

Rank the Qwen3.5 REAP 97B A10B Capabilities

🆘 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! 🌟

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? 54253 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer