Yi 6B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Yi 6B GPTQ   URL Share it on

Yi 6B GPTQ is an open-source language model by TheBloke. Features: 6b LLM, VRAM: 3.9GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.1.

  4-bit   Base model:01-ai/yi-6b Base model:quantized:01-ai/yi-...   Custom code   Gptq   Quantized   Region:us   Safetensors   Yi

Yi 6B GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Yi 6B GPTQ Parameters and Internals

Model Type 
text generation, bilingual (English/Chinese)
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Model provides high-quality inference with various quantization options. Compatibility with several inference engines.
Training Details 
Context Length:
4000
Input Output 
Output Format:
text
Release Notes 
Version:
Yi-6B
Date:
2023-11-02
Notes:
Initial release of the Yi-6B model with 4K sequence length extension to 32K during inference.
LLM NameYi 6B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Yi-6B-GPTQ 
Model NameYi 6B
Base Model(s)  Yi 6B   01-ai/Yi-6B
Model Size6b
Required VRAM3.9 GB
Updated2026-05-16
MaintainerTheBloke
Model Typeyi
Model Files  3.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureYiForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.35.0
Tokenizer ClassYiTokenizer
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Yi 6B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yi 6B 200K GPTQ195K / 3.9 GB162
...o Claude Puffin 8.0bpw H8 EXL2195K / 6.3 GB81
... Spicyboros 3.1 4.0bpw H6 EXL24K / 3.5 GB153
... Spicyboros 3.1 3.0bpw H6 EXL24K / 2.8 GB81
Yi 6B 200K Airo Claude Puffin195K / 12.1 GB61
Yi 6B 200K AWQ195K / 3.9 GB132
Dragon Yi 6B V04K / 3.7 GB110160
Dragon Yi 6B V0 AWQ4K / 3.9 GB142
01 Ai Yi 6B Openhermes4K / 12.1 GB174
Yi 6B Slimorca4K / 12.1 GB81
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Yi-6B-GPTQ.

Rank the Yi 6B GPTQ 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? 53999 in total.

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