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, HF Score: 51, LLM Explorer Score: 0.15, Arc: 53.4, HellaSwag: 71.5, MMLU: 56, TruthfulQA: 40.2, WinoGrande: 65.8, GSM8K: 19.4.
4-bit Autotrain compatible 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%
TruthfulQA: 40.16 vs 59 (gpt4)-31.9%
WinoGrande: 65.75 vs 87.5 (gpt4)-24.9%
GSM8K: 19.41 vs 96.4 (so35)-79.9%
LLME Score: 0.15433
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Deepseek Math 7B Instruct AWQ Q4 Parameters and Internals
| LLM Name | Deepseek Math 7B Instruct AWQ Q4 |
| Repository 🤗 | https://huggingface.co/hanspeterlyngsoeraaschoujensen/deepseek-math-7b-instruct-awq-Q4 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.8 GB |
| Updated | 2025-09-12 |
| Maintainer | hanspeterlyngsoeraaschoujensen |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq|q4 |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 102400 |
| Torch Data Type | float16 |
Best Alternatives to Deepseek Math 7B Instruct AWQ Q4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 2 7B 32K Instruct AWQ | 32K / 3.9 GB | 10 | 2 |
| CodeLlama 7B Instruct AWQ | 16K / 3.9 GB | 1279 | 4 |
| ...eechless Tora Code 7B V1.0 AWQ | 16K / 3.9 GB | 0 | 1 |
| ...ama 7B Instruct Hf W4 G128 AWQ | 16K / 3.9 GB | 6 | 0 |
| CausalLM 7B AWQ | 8K / 5.8 GB | 15 | 3 |
| Leo Hessianai 7B Chat AWQ | 8K / 3.9 GB | 12 | 1 |
| ...essianai 7B Chat Bilingual AWQ | 8K / 3.9 GB | 4 | 2 |
| Llama 2 7B Ft Instruct Es AWQ | 4K / 3.9 GB | 2 | 1 |
| Swallow 7B Instruct AWQ | 4K / 4.1 GB | 9 | 1 |
| ...i 7B Sft Qa Context Jaqket AWQ | 4K / 3.9 GB | 6 | 1 |
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! 🌟
What open-source LLMs or SLMs are you in search of? 51638 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20241124