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

Arcee Spark by arcee-ai

 »  All LLMs  »  arcee-ai  »  Arcee Spark   URL Share it on

  540   

Arcee Spark is an open-source language model by arcee-ai. Features: 7.6b LLM, VRAM: 15.2GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.23.

  Ar   Conversational   De   Deploy:azure   En   Endpoints compatible   Model-index   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/arcee-ai/Arcee-Spark 

Arcee Spark Benchmarks

MMLU Pro: 31.26
GPQA: 7.49
MUSR: 8.4
BBH: 36.92
IFEval: 57.18 vs 88 (so35)-35%
MATH Lvl 5: 11.4
LLME Score: 0.23035
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Arcee Spark (arcee-ai/Arcee-Spark)
🌟 Advertise your project 🚀

Arcee Spark Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
business, real-time applications, edge computing, cost-effective scaling, rapid prototyping, on-premise deployment
Applications:
chatbots, customer service automation, interactive systems, edge devices, AI-powered features
Primary Use Cases:
real-time applications, rapid prototyping, edge computing, on-premise deployment
Additional Notes 
Arcee Spark demonstrates that bigger isn't always better. By leveraging advanced training techniques and architectural optimizations, it delivers speed, efficiency, and flexibility. Despite its compact size, Arcee Spark offers deep reasoning capabilities.
Supported Languages 
en (full), de (partial), ar (partial)
Training Details 
Data Volume:
1.8 million samples
Methodology:
Fine-tuned, merged with Qwen2-7B-Instruct using Arcee's mergekit and further refined using Direct Preference Optimization (DPO)
Context Length:
128000
LLM NameArcee Spark
Repository 🤗https://huggingface.co/arcee-ai/Arcee-Spark 
Model Size7.6b
Required VRAM15.2 GB
Updated2026-02-14
Maintainerarcee-ai
Model Typeqwen2
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4
Supported Languagesen de ar
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Arcee Spark

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5128K / 15.2 GB50
A.X 4.0128K / 144.4 GB539173
Palmyra Mini Thinking B128K / 3.5 GB2127
XJJ DeepSeek R1 COT128K / 0.1 GB50
SuperNova Medius Bf16128K / 29.6 GB62
C3D4e5F6128K / 1 GB6300
Qwerty2 05bita128K / 1 GB5690
B2C3D4e5128K / 1 GB500
Mxbai Rerank Large V232K / 3.1 GB6658127
KYRA 1.0X Horizon32K / 29.7 GB51
Note: green Score (e.g. "73.2") means that the model is better than arcee-ai/Arcee-Spark.

Rank the Arcee Spark 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? 52554 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