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

Deepseek Math 7B Instruct AWQ Q4 by hanspeterlyngsoeraaschoujensen

 »  All LLMs  »  hanspeterlyngsoeraaschoujensen  »  Deepseek Math 7B Instruct AWQ Q4   URL Share it on

  7   

Deepseek Math 7B Instruct AWQ Q4 is an open-source language model by hanspeterlyngsoeraaschoujensen. Features: 7b LLM, VRAM: 4.8GB, Context: 4K, Quantized, Instruction-Based, LLM Explorer Score: 0.14, Arc: 53.4, HellaSwag: 71.5, MMLU: 56, GSM8K: 19.4.

  4-bit   Awq   Conversational   Endpoints compatible   Instruct   Llama   Q4   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/hanspeterlyngsoeraaschoujensen/deepseek-math-7b-instruct-awq-Q4 

Deepseek Math 7B Instruct AWQ Q4 Benchmarks

ARC: 53.41 vs 96.7 (so35)-44.8%
HellaSwag: 71.5 vs 95.3 (gpt4)-25%
MMLU: 55.97 vs 88.3 (so35)-36.6%
GSM8K: 19.41 vs 96.4 (so35)-79.9%
LLME Score: 0.14123
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Math 7B Instruct AWQ Q4 (hanspeterlyngsoeraaschoujensen/deepseek-math-7b-instruct-awq-Q4)
🌟 Advertise your project 🚀

Deepseek Math 7B Instruct AWQ Q4 Parameters and Internals

LLM NameDeepseek Math 7B Instruct AWQ Q4
Repository 🤗https://huggingface.co/hanspeterlyngsoeraaschoujensen/deepseek-math-7b-instruct-awq-Q4 
Base Model(s)  Deepseek Math 7B Instruct   deepseek-ai/deepseek-math-7b-instruct
Model Size7b
Required VRAM4.8 GB
Updated2026-05-25
Maintainerhanspeterlyngsoeraaschoujensen
Model Typellama
Instruction-BasedYes
Model Files  4.8 GB
AWQ QuantizationYes
Quantization Typeawq|q4
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size102400
Torch Data Typefloat16

Best Alternatives to Deepseek Math 7B Instruct AWQ Q4

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB132
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB71
CodeLlama 7B Instruct AWQ16K / 3.9 GB684
...ama 7B Instruct Hf W4 G128 AWQ16K / 3.9 GB60
CausalLM 7B AWQ8K / 5.8 GB103
...essianai 7B Chat Bilingual AWQ8K / 3.9 GB152
Leo Hessianai 7B Chat AWQ8K / 3.9 GB131
Llama 2 7B Ft Instruct Es AWQ4K / 3.9 GB91
Swallow 7B Instruct AWQ4K / 4.1 GB81
...i 7B Sft Qa Context Jaqket AWQ4K / 3.9 GB41

Rank the Deepseek Math 7B Instruct AWQ Q4 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? 54415 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