What are the hardware requirements for Deepseek Math 7B Instruct GPTQ?

Deepseek Math 7B Instruct GPTQ requires approximately 4.8 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Math 7B Instruct GPTQ and how large is it?

Deepseek Math 7B Instruct GPTQ is developed by hanspeterlyngsoeraaschoujensen, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Deepseek Math 7B Instruct GPTQ perform on standard benchmarks?

Deepseek Math 7B Instruct GPTQ has the following published scores: MMLU 55.97. Compare against reference models on this page or on the LLM Explorer leaderboards.

Deepseek Math 7B Instruct GPTQ by hanspeterlyngsoeraaschoujensen — VRAM 4.8GB, 4K context

Name: Deepseek Math 7B Instruct GPTQ
Author: hanspeterlyngsoeraaschoujensen

Deepseek Math 7B Instruct GPTQ is an open-source language model by hanspeterlyngsoeraaschoujensen. Features: 7b LLM, VRAM: 4.8GB, Context: 4K, Quantized, Instruction-Based, LLM Explorer Score: 0.13, Arc: 53.4, HellaSwag: 71.5, MMLU: 56, GSM8K: 19.4.

Arxiv:1910.09700 4-bit Endpoints compatible Gptq Instruct Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/hanspeterlyngsoeraaschoujensen/deepseek-math-7b-instruct-GPTQ

Deepseek Math 7B Instruct GPTQ Parameters and Internals

LLM Name	Deepseek Math 7B Instruct GPTQ
Repository 🤗	https://huggingface.co/hanspeterlyngsoeraaschoujensen/deepseek-math-7b-instruct-GPTQ
Base Model(s)	Deepseek Math 7B Instruct deepseek-ai/deepseek-math-7b-instruct
Model Size	7b
Required VRAM	4.8 GB
Updated	2026-07-29
Maintainer	hanspeterlyngsoeraaschoujensen
Model Type	llama
Instruction-Based	Yes
Model Files	4.8 GB
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	LlamaForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.2
Vocabulary Size	102400
Torch Data Type	bfloat16

Rank the Deepseek Math 7B Instruct GPTQ capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Deepseek Math 7B Instruct GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
... 7B 32K Instructions V4 Marlin	32K / 4.1 GB	8	0
Llama 2 7B 32K Instruct GPTQ	32K / 3.9 GB	49	27
...a 7B Instruct GPTQ Calib Ja 1K	16K / 3.9 GB	6	0
...echless Tora Code 7B V1.0 GPTQ	16K / 3.9 GB	9	1
CodeLlama 7B Instruct GPTQ	16K / 3.9 GB	499	46
CausalLM 7B GPTQ	8K / 5.9 GB	7	5
Leo Hessianai 7B Chat GPTQ	8K / 3.9 GB	18	0
...ssianai 7B Chat Bilingual GPTQ	8K / 3.9 GB	6	0
Xgen 7B 8K Open Instruct Gptq	8K / 4.2 GB	5	4
... Llama 2 7B Fast Instruct GPTQ	4K / 4.1 GB	95	3