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

Kyllene 34B V1.1 2.8bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Kyllene 34B V1.1 2.8bpw H6 EXL2   URL Share it on

  18   
  Autotrain compatible   Conversational   Endpoints compatible   Exl2   Llama   Merge   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Kyllene-34B-v1.1-2.8bpw-h6-exl2 

Kyllene 34B V1.1 2.8bpw H6 EXL2 Benchmarks

LLME Score: 0.1511
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kyllene 34B V1.1 2.8bpw H6 EXL2 (LoneStriker/Kyllene-34B-v1.1-2.8bpw-h6-exl2)

Kyllene 34B V1.1 2.8bpw H6 EXL2 Parameters and Internals

Use Cases 
Limitations:
Model can produce NSFW content.
Additional Notes 
MergeMonster method works but consumes large amounts of RAM or VRAM and takes a really long time to process model data.
Training Details 
Data Volume:
200K context length
Methodology:
A result of a new merge method provided by MergeMonster tool with extended RPG preset. Method aims to maximize probability of certain phrases and minimize probability of other phrases.
Context Length:
200000
Training Time:
24H
Hardware Used:
1x ADA6000
LLM NameKyllene 34B V1.1 2.8bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/Kyllene-34B-v1.1-2.8bpw-h6-exl2 
Model Size34b
Required VRAM13 GB
Updated2025-06-02
MaintainerLoneStriker
Model Typellama
Model Files  8.6 GB: 1-of-2   4.4 GB: 2-of-2
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length200000
Model Max Length200000
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typefloat16

Best Alternatives to Kyllene 34B V1.1 2.8bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...34B 200K Aezakmi Raw 1902 EXL2195K / 20.7 GB151
Yi 34B 200K MAR2024 EXL2 4bpw195K / 18 GB221
...mi Raw Toxic 2702 4.65bpw EXL2195K / 20.8 GB192
...B 200K RPMerge 4.65bpw H6 EXL2195K / 10.5 GB91
Yi 34B 200K RPMerge195K / 68.9 GB1560
Opus V1 34B 8.0bpw H8 EXL2195K / 34.8 GB191
Opus V1 34B 5.0bpw H6 EXL2195K / 22.3 GB152
Opus V1 34B 4.0bpw H6 EXL2195K / 18 GB121
34B Beta 5.0bpw H6 EXL2195K / 22.3 GB191
34B Beta 4.0bpw H6 EXL2195K / 18.1 GB101
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Kyllene-34B-v1.1-2.8bpw-h6-exl2.

Rank the Kyllene 34B V1.1 2.8bpw H6 EXL2 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? 47796 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 v20241227
  Support LLM Explorer