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

UndiMix V1 13B by Undi95

 »  All LLMs  »  Undi95  »  UndiMix V1 13B   URL Share it on

  744   

UndiMix V1 13B is an open-source language model by Undi95. Features: 13b LLM, VRAM: 26.7GB, Context: 4K, License: cc-by-nc-4.0, Quantized, HF Score: 55.5, LLM Explorer Score: 0.12, Arc: 59.5, HellaSwag: 82.5, MMLU: 55.8, TruthfulQA: 49.8, WinoGrande: 75.5, GSM8K: 10.

  Endpoints compatible   Fp16   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Undi95/UndiMix-v1-13b 

UndiMix V1 13B Benchmarks

ARC: 59.47 vs 96.7 (so35)-38.5%
HellaSwag: 82.45 vs 95.3 (gpt4)-13.5%
MMLU: 55.83 vs 88.3 (so35)-36.8%
TruthfulQA: 49.78 vs 59 (gpt4)-15.6%
WinoGrande: 75.45 vs 87.5 (gpt4)-13.8%
GSM8K: 10.01 vs 96.4 (so35)-89.6%
LLME Score: 0.12244
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
UndiMix V1 13B (Undi95/UndiMix-v1-13b)
🌟 Advertise your project 🚀

UndiMix V1 13B Parameters and Internals

Model Type 
text generation
Additional Notes 
Created using a mix of models for diverse response styles.
Input Output 
Input Format:
Alpaca prompt template
Output Format:
Response that completes the request.
LLM NameUndiMix V1 13B
Repository 🤗https://huggingface.co/Undi95/UndiMix-v1-13b 
Model Size13b
Required VRAM26.7 GB
Updated2026-04-02
MaintainerUndi95
Model Typellama
Model Files  10.3 GB: 1-of-3   9.9 GB: 2-of-3   6.5 GB: 3-of-3
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.32.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the UndiMix V1 13B

Model
Likes
Downloads
VRAM
UndiMix V1 13B AWQ197 GB
UndiMix V1 13B GGUF1495 GB
UndiMix V1 13B GPTQ147 GB
UndiMix V1 13B GGML1155 GB

Best Alternatives to UndiMix V1 13B

Best Alternatives
Context / RAM
Downloads
Likes
Llama13b 32K Illumeet Finetune32K / 26 GB50
...Maid V3 13B 32K 6.0bpw H6 EXL232K / 10 GB41
...Maid V3 13B 32K 8.0bpw H8 EXL232K / 13.2 GB31
WhiteRabbitNeo 13B V116K / 26 GB2921450
CodeLlama 13B Python Fp1616K / 26 GB144725
CodeLlama 13B Instruct Fp1616K / 26 GB90328
CodeLlama 13B Fp1616K / 26 GB3867
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB3463
Codellama 13B Bnb 4bit16K / 7.2 GB885
Airophin 13B Pntk 16K Fp1616K / 26 GB3804
Note: green Score (e.g. "73.2") means that the model is better than Undi95/UndiMix-v1-13b.

Rank the UndiMix V1 13B 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? 53205 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