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 Coder REAP 363B A35B by cerebras

 »  All LLMs  »  cerebras  »  Qwen3 Coder REAP 363B A35B   URL Share it on

  17   

Qwen3 Coder REAP 363B A35B is an open-source language model by cerebras. Features: 480b LLM, VRAM: 215GB, Context: 256K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.22.

  Arxiv:2510.13999 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-coder-48...   Codegen   Compression   Conversational   En   Endpoints compatible   Instruct   Moe   Pruning   Qwen-coder   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cerebras/Qwen3-Coder-REAP-363B-A35B 

Qwen3 Coder REAP 363B A35B Benchmarks

LLME Score: 0.21573
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 Coder REAP 363B A35B (cerebras/Qwen3-Coder-REAP-363B-A35B)
🌟 Advertise your project 🚀

Qwen3 Coder REAP 363B A35B Parameters and Internals

LLM NameQwen3 Coder REAP 363B A35B
Repository 🤗https://huggingface.co/cerebras/Qwen3-Coder-REAP-363B-A35B 
Base Model(s)  Qwen3 Coder 480B A35B Instruct   Qwen/Qwen3-Coder-480B-A35B-Instruct
Model Size480b
Required VRAM215 GB
Updated2026-06-07
Maintainercerebras
Model Typeqwen3_moe
Instruction-BasedYes
Model Files  5.0 GB: 1-of-146   5.0 GB: 2-of-146   5.0 GB: 3-of-146   5.0 GB: 4-of-146   5.0 GB: 5-of-146   5.0 GB: 6-of-146   5.0 GB: 7-of-146   5.0 GB: 8-of-146   5.0 GB: 9-of-146   5.0 GB: 10-of-146   5.0 GB: 11-of-146   5.0 GB: 12-of-146   5.0 GB: 13-of-146   5.0 GB: 14-of-146   5.0 GB: 15-of-146   5.0 GB: 16-of-146   5.0 GB: 17-of-146   5.0 GB: 18-of-146   5.0 GB: 19-of-146   5.0 GB: 20-of-146   5.0 GB: 21-of-146   5.0 GB: 22-of-146   5.0 GB: 23-of-146   5.0 GB: 24-of-146   5.0 GB: 25-of-146   5.0 GB: 26-of-146   5.0 GB: 27-of-146   5.0 GB: 28-of-146   5.0 GB: 29-of-146   5.0 GB: 30-of-146   5.0 GB: 31-of-146   5.0 GB: 32-of-146   5.0 GB: 33-of-146   5.0 GB: 34-of-146   5.0 GB: 35-of-146   5.0 GB: 36-of-146   5.0 GB: 37-of-146   5.0 GB: 38-of-146   5.0 GB: 39-of-146   5.0 GB: 40-of-146   5.0 GB: 41-of-146   5.0 GB: 42-of-146   5.0 GB: 43-of-146
Supported Languagesen
Generates CodeYes
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.1
Vocabulary Size151936

Best Alternatives to Qwen3 Coder REAP 363B A35B

Best Alternatives
Context / RAM
Downloads
Likes
...n3 Coder 480B A35B Instruct 1M1024K / 171.9 GB787
Qwen3 Coder 480B A35B Instruct256K / 171.9 GB273301336
Qwen3 Coder 480B A35B Instruct256K / 167.9 GB474
...3 Coder 480B A35B Instruct FP8256K / 429.8 GB182851151
...Coder 480B A35B Instruct NVFP4256K / 210 GB67912
...3 Coder 480B A35B Instruct FP8256K / 429.8 GB228
... Coder 480B A35B Instruct 4bit256K / 185.6 GB339419
Note: green Score (e.g. "73.2") means that the model is better than cerebras/Qwen3-Coder-REAP-363B-A35B.

Rank the Qwen3 Coder REAP 363B A35B 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? 54415 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