What are the hardware requirements for Chinese Llama 2 13B?

Chinese Llama 2 13B requires approximately 26.5 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 Chinese Llama 2 13B and how large is it?

Chinese Llama 2 13B is developed by hfl, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Chinese Llama 2 13B perform on standard benchmarks?

Chinese Llama 2 13B has the following published scores: MMLU 52.94. Compare against reference models on this page or on the LLM Explorer leaderboards.

Chinese Llama 2 13B by hfl — VRAM 26.5GB, 4K context

Name: Chinese Llama 2 13B
Author: hfl

Chinese Llama 2 13B is an open-source language model by hfl. Features: 13b LLM, VRAM: 26.5GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.14, Arc: 55.8, HellaSwag: 79.5, MMLU: 52.9, GSM8K: 9.8.

En Endpoints compatible Llama Pytorch Region:us Sharded Zh

Model Card on HF 🤗: https://huggingface.co/hfl/chinese-llama-2-13b

Chinese Llama 2 13B Parameters and Internals

Model Type

full-parameter model, instruction-following model

Additional Notes

Chinese-LLaMA-2-7B is part of the second generation of the Chinese LLaMA & Alpaca LLM project, and it's based on Llama-2 by Meta. It supports a 4K context and can be expanded up to 18K+ using the NTK method. It uses a new extended Chinese vocabulary beyond Llama-2 and has been improved by large-scale Chinese data for better semantic understanding.

Supported Languages

zh (High), en (High)

LLM Name	Chinese Llama 2 13B
Repository 🤗	https://huggingface.co/hfl/chinese-llama-2-13b
Model Size	13b
Required VRAM	26.5 GB
Updated	2026-07-09
Maintainer	hfl
Model Type	llama
Model Files	10.2 GB: 1-of-3 9.9 GB: 2-of-3 6.4 GB: 3-of-3
Supported Languages	zh en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.32.0.dev0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	55296
Torch Data Type	float16

Rank the Chinese Llama 2 13B 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 Chinese Llama 2 13B

Model	Likes	Downloads	VRAM
Chinese Llama 2 13B Gguf	5	310	5 GB

Best Alternatives to Chinese Llama 2 13B

Best Alternatives	Context / RAM	Downloads	Likes
Luminaura RP 13B	128K / 26 GB	9	1
Yarn Llama 2 13B 128K	128K / 26 GB	184	113
Agent Llama2 13B 80K	80K / 26.4 GB	5	0
Chat Llama2 13B 80K	80K / 52.8 GB	5	0
LongAlign 13B 64K	64K / 26 GB	96	13
LongAlign 13B 64K Base	64K / 26 GB	89	3
LongAlign 13B 64K	64K / 26 GB	11	13
LongAlign 13B 64K Base	64K / 26 GB	6	3
Openbuddy Llama2 13B V15p1 64K	64K / 26.1 GB	4	4
Openbuddy Llama2 13b64k V15	64K / 26.1 GB	12	2