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

Openchat 3.5 1210 AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Openchat 3.5 1210 AWQ   URL Share it on

  21   

Openchat 3.5 1210 AWQ is an open-source language model by TheBloke. Features: 7.2b LLM, VRAM: 4.2GB, Context: 8K, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.

  Arxiv:2212.10560   Arxiv:2303.08774   Arxiv:2309.11235   4-bit   Awq Base model:openchat/openchat-3... Base model:quantized:openchat/...   C-rlft   Conversational Dataset:glaiveai/glaive-code-a...   Dataset:imone/openorca flan Dataset:kaist-ai/feedback-coll... Dataset:ldjnr/lesswrong-amplif...   Dataset:ldjnr/pure-dove   Dataset:ldjnr/verified-camel   Dataset:meta-math/metamathqa Dataset:openassistant/oasst to... Dataset:openchat/openchat shar...   Dataset:tiedong/goat   Dataset:tiger-lab/mathinstruct   Mistral   Openchat   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/openchat-3.5-1210-AWQ 

Openchat 3.5 1210 AWQ Benchmarks

LLME Score: 0.11657
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Openchat 3.5 1210 AWQ (TheBloke/openchat-3.5-1210-AWQ)
🌟 Advertise your project 🚀

Openchat 3.5 1210 AWQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, general purpose text generation
Applications:
coding, general queries, mathematical reasoning
Primary Use Cases:
chat, code assistance, math problem solving
Limitations:
bound by limitations inherent in its foundation models, may hallucinate information, potential to generate harmful or biased responses
Considerations:
Additional AI safety measures are recommended for use cases requiring safe and moderated responses.
Additional Notes 
Model emphasizes high-throughput deployment using vLLM, applicable for consumer-grade GPUs.
Training Details 
Data Sources:
openchat/openchat_sharegpt4_dataset, kaist-ai/Feedback-Collection, imone/OpenOrca_FLAN, LDJnr/LessWrong-Amplify-Instruct, LDJnr/Pure-Dove, LDJnr/Verified-Camel, tiedong/goat, glaiveai/glaive-code-assistant, meta-math/MetaMathQA, OpenAssistant/oasst_top1_2023-08-25, TIGER-Lab/MathInstruct
Methodology:
Quantized using AWQ, a low-bit weight quantization method supporting 4-bit quantization.
Context Length:
4096
Hardware Used:
mass compute hardware
Model Architecture:
Mistral
Input Output 
Input Format:
GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
Accepted Modalities:
text
Release Notes 
Version:
1210
Date:
December 10, 2023
Notes:
15-point improvement in coding over OpenChat-3.5, supports two modes (Coding + Generalist, Mathematical Reasoning), added experimental evaluator capabilities.
LLM NameOpenchat 3.5 1210 AWQ
Repository 🤗https://huggingface.co/TheBloke/openchat-3.5-1210-AWQ 
Model NameOpenchat 3.5 1210
Model CreatorOpenChat
Base Model(s)  openchat/openchat-3.5-1210   openchat/openchat-3.5-1210
Model Size7.2b
Required VRAM4.2 GB
Updated2025-12-31
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Openchat 3.5 1210 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Hc Mistral Alpaca Merged AWQ32K / 4.2 GB90
Phoenix AWQ32K / 4.2 GB131
Mistral Ft Optimized 1227 AWQ32K / 4.2 GB51
Metis 0.5 AWQ32K / 4.2 GB21
XDAN L1 Chat RL V1 AWQ32K / 4.2 GB61
Apricot Wildflower 20 AWQ32K / 4.2 GB31
OpenZephyrChat V0.2 AWQ32K / 4.2 GB83
Ana V1 M7 AWQ32K / 4.2 GB12
OpenZephyrChat AWQ32K / 4.2 GB42
...2.5 Neural Chat V3.3 Slerp AWQ32K / 4.2 GB21
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/openchat-3.5-1210-AWQ.

Rank the Openchat 3.5 1210 AWQ 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? 51631 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 v20241124
  Support LLM Explorer