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

Marx 3B by acrastt

 »  All LLMs  »  acrastt  »  Marx 3B   URL Share it on

  1871   
  Autotrain compatible Dataset:totally-not-an-llm/eve...   En   Endpoints compatible   Llama   Model-index   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/acrastt/Marx-3B 

Marx 3B Benchmarks

ARC: 43.17 vs 96.7 (so35)-55.4%
HellaSwag: 72.68 vs 95.3 (gpt4)-23.7%
MMLU: 28.46 vs 88.3 (so35)-67.8%
TruthfulQA: 39.09 vs 59 (gpt4)-33.7%
WinoGrande: 65.59 vs 87.5 (gpt4)-25%
GSM8K: 1.29 vs 96.4 (so35)-98.7%
LLME Score: 0.15647
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Marx 3B (acrastt/Marx-3B)
🌟 Advertise your project 🚀

Marx 3B Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model was an initial experiment in finetuning, so performance may vary significantly from expectations. Available in GGML and GPTQ quantizations for different deployment environments.
Training Details 
Data Sources:
EverythingLM Data(ShareGPT format more cleaned)
Data Volume:
unknown
Methodology:
finetuning
Training Time:
1 epoch
Input Output 
Input Format:
{prompt}
Output Format:
text
Performance Tips:
Don't expect high performance as it was a finetuning experiment
LLM NameMarx 3B
Repository 🤗https://huggingface.co/acrastt/Marx-3B 
Model Size3b
Required VRAM6.8 GB
Updated2025-09-23
Maintaineracrastt
Model Typellama
Model Files  6.8 GB   6.8 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.30.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Marx 3B

Best Alternatives
Context / RAM
Downloads
Likes
ISA 03 Mini 3B Hybrid Preview256K / 6.5 GB8514
Llama 3.2 3B Instruct128K / 6.5 GB16749181724
Llama 3.2 3B128K / 6.5 GB616308634
DeepSeek R1 Distill Llama 3B128K / 6.5 GB133116
Hermes 3 Llama 3.2 3B128K / 6.5 GB5468172
FuseChat Llama 3.2 3B Instruct128K / 6.5 GB14817
Orpheus 3B 0.1 Ft128K / 6.6 GB374808
Discord Micae Hermes 3 3B128K / 6.5 GB11159
Llama 3.2 3B Instruct128K / 6.5 GB42213275
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB42
Note: green Score (e.g. "73.2") means that the model is better than acrastt/Marx-3B.

Rank the Marx 3B 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? 51534 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.
Release v20241124
  Support LLM Explorer