Spreadsheet RL 4B by Spreadsheet-RL

 »  All LLMs  »  Spreadsheet-RL  »  Spreadsheet RL 4B   URL Share it on

Spreadsheet RL 4B is an open-source language model by Spreadsheet-RL. Features: 4b LLM, VRAM: 8.8GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.31.

  Arxiv:2605.22642   Agents Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b-think...   Conversational Dataset:spreadsheet-rl/spreads...   En   Endpoints compatible   Excel   Grpo   Qwen3   Region:us   Safetensors   Spreadsheet   Tool-use   Verl

Spreadsheet RL 4B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Spreadsheet RL 4B Parameters and Internals

LLM NameSpreadsheet RL 4B
Repository 🤗https://huggingface.co/Spreadsheet-RL/Spreadsheet-RL-4B 
Base Model(s)  Qwen3 4B Thinking 2507   Qwen/Qwen3-4B-Thinking-2507
Model Size4b
Required VRAM8.8 GB
Updated2026-05-24
MaintainerSpreadsheet-RL
Model Typeqwen3
Model Files  8.8 GB
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.3.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Spreadsheet RL 4B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB6454164853
GRPO 4 70256K / 8.1 GB50
Qwen3 4B Thinking 2507256K / 8.1 GB830285581
Lightning 4B256K / 8.1 GB136
Jan V1 4B256K / 8.1 GB108354353
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB80378075
CyberSecQwen 4B256K / 8 GB73611
OpenSonnet Lite256K / 8.1 GB30024
ChineseErrorCorrector4 4B256K / 8.1 GB1574
AgentCPM Explore256K / 8.9 GB204413
Note: green Score (e.g. "73.2") means that the model is better than Spreadsheet-RL/Spreadsheet-RL-4B.

Rank the Spreadsheet RL 4B 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? 53942 in total.

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