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

WizardLM 30B V1.0 GPTQ by localmodels

 »  All LLMs  »  localmodels  »  WizardLM 30B V1.0 GPTQ   URL Share it on

  2   

WizardLM 30B V1.0 GPTQ is an open-source language model by localmodels. Features: 30b LLM, VRAM: 16.9GB, Context: 2K, Quantized, LLM Explorer Score: 0.1, Arc: 62.5, HellaSwag: 83.3, MMLU: 59.1, GSM8K: 21.8.

  Endpoints compatible   Gptq   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/localmodels/WizardLM-30B-v1.0-GPTQ 

WizardLM 30B V1.0 GPTQ Benchmarks

ARC: 62.54 vs 96.7 (so35)-35.3%
HellaSwag: 83.27 vs 95.3 (gpt4)-12.6%
MMLU: 59.05 vs 88.3 (so35)-33.1%
GSM8K: 21.83 vs 96.4 (so35)-77.4%
LLME Score: 0.09512
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
WizardLM 30B V1.0 GPTQ (localmodels/WizardLM-30B-v1.0-GPTQ)
🌟 Advertise your project 🚀

WizardLM 30B V1.0 GPTQ Parameters and Internals

Model Type 
Text Generation
Additional Notes 
The model uses wizardlm-30b-1.0-4bit.safetensors and works with both Triton and CUDA branches as well as AutoGPTQ. The parameter 'Groupsize' is set to None and uses --act-order.
LLM NameWizardLM 30B V1.0 GPTQ
Repository 🤗https://huggingface.co/localmodels/WizardLM-30B-v1.0-GPTQ 
Base Model(s)  LLMs/WizardLM-30B-V1.0   LLMs/WizardLM-30B-V1.0
Model Size30b
Required VRAM16.9 GB
Updated2026-05-04
Maintainerlocalmodels
Model Typellama
Model Files  16.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.30.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32001
Torch Data Typefloat16

Best Alternatives to WizardLM 30B V1.0 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
GPlatty 30B SuperHOT 8K GPTQ8K / 16.9 GB767
Tulu 30B SuperHOT 8K GPTQ8K / 16.9 GB685
... 30B Supercot SuperHOT 8K GPTQ8K / 16.9 GB95
Platypus 30B SuperHOT 8K GPTQ8K / 16.9 GB104
Yayi2 30B Llama GPTQ4K / 17 GB112
WizardLM 30B GPTQ2K / 16.9 GB22918
...2 Llama 30B 7K Steps Gptq 2bit2K / 9.5 GB82
Llama 30B FINAL MODEL MINI2K / 19.4 GB71
...Assistant SFT 7 Llama 30B GPTQ2K / 16.9 GB21835
...2 Llama 30B 7K Steps Gptq 4bit2K / 17.5 GB73
Note: green Score (e.g. "73.2") means that the model is better than localmodels/WizardLM-30B-v1.0-GPTQ.

Rank the WizardLM 30B V1.0 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.

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