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

Qwen1.5 110B Chat 3.25bpw H6 EXL2 by yiximail

 »  All LLMs  »  yiximail  »  Qwen1.5 110B Chat 3.25bpw H6 EXL2   URL Share it on

  9   

Qwen1.5 110B Chat 3.25bpw H6 EXL2 is an open-source language model by yiximail. Features: 110b LLM, VRAM: 47.7GB, Context: 32K, License: other, Quantized, LLM Explorer Score: 0.13.

  Arxiv:2309.16609   Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Exl2   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/yiximail/Qwen1.5-110B-Chat-3.25bpw-h6-exl2 

Qwen1.5 110B Chat 3.25bpw H6 EXL2 Benchmarks

LLME Score: 0.1317
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen1.5 110B Chat 3.25bpw H6 EXL2 (yiximail/Qwen1.5-110B-Chat-3.25bpw-h6-exl2)
🌟 Advertise your project 🚀

Qwen1.5 110B Chat 3.25bpw H6 EXL2 Parameters and Internals

Model Type 
text-generation
Training Details 
Methodology:
Pretrained with supervised finetuning and direct preference optimization.
Context Length:
32768
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention.
Input Output 
Performance Tips:
If you encounter code switching or other bad cases, use provided hyper-parameters in `generation_config.json`.
LLM NameQwen1.5 110B Chat 3.25bpw H6 EXL2
Repository 🤗https://huggingface.co/yiximail/Qwen1.5-110B-Chat-3.25bpw-h6-exl2 
Model Size110b
Required VRAM47.7 GB
Updated2025-01-18
Maintaineryiximail
Model Typeqwen2
Model Files  8.6 GB: 1-of-6   8.5 GB: 2-of-6   8.6 GB: 3-of-6   8.4 GB: 4-of-6   8.5 GB: 5-of-6   5.1 GB: 6-of-6
Supported Languagesen
Quantization Typeexl2
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 110B Chat 3.25bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Qwen1.5 110B Chat 4bit32K / 62.2 GB295
Qwen1.5 110B Chat 8bit32K / 179.8 GB81
...n1.5 110B Chat 3.35bpw H6 EXL232K / 49 GB81
Qwen1.5 110B 4bit8K / 62.2 GB61
Qwen1.5 110B Chat32K / 158.3 GB2344133
Qwen1.5 110B32K / 221.7 GB466103
Qwen1.5 110B Chat AWQ32K / 61.7 GB1636059
Qwen1.5 110B Chat AWQ32K / 61.1 GB50
Dolphin 2.9.1 Qwen 110B32K / 193.4 GB1928
Dolphin 2.9.1 Qwen 110B32K / 193.4 GB729
Note: green Score (e.g. "73.2") means that the model is better than yiximail/Qwen1.5-110B-Chat-3.25bpw-h6-exl2.

Rank the Qwen1.5 110B Chat 3.25bpw 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? 52721 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