What are the hardware requirements for Deepseek Math Full Sft?

Deepseek Math Full Sft requires approximately 13.8 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 Full Sft and how large is it?

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

Where can I download or evaluate Deepseek Math Full Sft?

Deepseek Math Full Sft is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Deepseek Math Full Sft by formalmathatepfl — VRAM 13.8GB, 4K context

Name: Deepseek Math Full Sft
Author: formalmathatepfl

Deepseek Math Full Sft is an open-source language model by formalmathatepfl. Features: 7b LLM, VRAM: 13.8GB, Context: 4K, License: other, LLM Explorer Score: 0.23.

Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Conversational Endpoints compatible Full Generated from trainer Llama Llama-factory Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/formalmathatepfl/deepseek-math-full-sft

Deepseek Math Full Sft Parameters and Internals

LLM Name	Deepseek Math Full Sft
Repository 🤗	https://huggingface.co/formalmathatepfl/deepseek-math-full-sft
Base Model(s)	Deepseek Math 7B Base deepseek-ai/deepseek-math-7b-base
Model Size	7b
Required VRAM	13.8 GB
Updated	2026-05-05
Maintainer	formalmathatepfl
Model Type	llama
Model Files	13.8 GB 0.0 GB
Model Architecture	LlamaForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<｜end▁of▁sentence｜>
Vocabulary Size	102400

Rank the Deepseek Math Full Sft 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 Full Sft

Best Alternatives	Context / RAM	Downloads
124	1024K / 16.1 GB	93
162	1024K / 16.1 GB	60
157	1024K / 16.1 GB	101
118	1024K / 16.1 GB	15
A5.4	1024K / 16.1 GB	12
A3.4	1024K / 16.1 GB	13
A2.4	1024K / 16.1 GB	12
A6 L	1024K / 16.1 GB	201
M	1024K / 16.1 GB	127
2 Very Sci Fi	1024K / 16.1 GB	317