What are the hardware requirements for OpenMath CodeLlama 13B Python Hf?

OpenMath CodeLlama 13B Python Hf requires approximately 26 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OpenMath CodeLlama 13B Python Hf and how large is it?

OpenMath CodeLlama 13B Python Hf is developed by nvidia, a model with 13b 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 OpenMath CodeLlama 13B Python Hf?

OpenMath CodeLlama 13B Python Hf is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OpenMath CodeLlama 13B Python Hf by nvidia — VRAM 26GB, 16K context

Name: OpenMath CodeLlama 13B Python Hf
Author: nvidia

OpenMath CodeLlama 13B Python Hf is an open-source language model by nvidia. Features: 13b LLM, VRAM: 26GB, Context: 16K, License: llama2, Code Generating, LLM Explorer Score: 0.11.

Arxiv:2402.10176 Base model:codellama/codellama... Base model:finetune:codellama/... Code Codegen Dataset:nvidia/openmathinstruc... En Endpoints compatible Llama Math Nvidia Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nvidia/OpenMath-CodeLlama-13b-Python-hf

OpenMath CodeLlama 13B Python Hf Parameters and Internals

Model Type

mathematical problem solving, text-based reasoning, Python code execution

Use Cases

Areas:

research, commercial applications

Primary Use Cases:

solve mathematical problems, integrate text-based reasoning with code execution

Additional Notes

The model solves mathematical problems by integrating text-based reasoning with code blocks executed by Python interpreter. A pipeline is fully open-sourced.

Supported Languages

en (Proficient)

Training Details

Data Sources:

nvidia/OpenMathInstruct-1

Data Volume:

1.8M problem-solution pairs

Methodology:

Trained using a math instruction tuning dataset generated with Mixtral-8x7B model.

LLM Name	OpenMath CodeLlama 13B Python Hf
Repository 🤗	https://huggingface.co/nvidia/OpenMath-CodeLlama-13b-Python-hf
Base Model(s)	CodeLlama 13B Python Hf codellama/CodeLlama-13b-Python-hf
Model Size	13b
Required VRAM	26 GB
Updated	2026-07-13
Maintainer	nvidia
Model Type	llama
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3
Supported Languages	en
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.37.2
Tokenizer Class	CodeLlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the OpenMath CodeLlama 13B Python Hf 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

Quantized Models of the OpenMath CodeLlama 13B Python Hf

Model	Likes	Downloads	VRAM
...th CodeLlama 13B Python Hf AWQ	0	6	7 GB

Best Alternatives to OpenMath CodeLlama 13B Python Hf

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B Instruct Hf	16K / 26 GB	2469	160
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Hf	16K / 26 GB	3466	117
Tora Code 13B V1.0	16K / 26 GB	878	15
CodeLlama 13B Python Hf	16K / 26 GB	558	51
...ma 13B Hf Truncated Embeddings	16K / 52.3 GB	5	0
...ma Airoboros Orca Platypus 13B	16K / 26 GB	117	0
Codellama 13B Oasst Sft V10	16K / 25.9 GB	184	70
CodeLlama 13B Hf	16K / 26 GB	224	0

Note: green Score (e.g. "73.2") means that the model is better than nvidia/OpenMath-CodeLlama-13b-Python-hf.