What are the hardware requirements for LongCite Llama3.1 8B?

LongCite Llama3.1 8B requires approximately 16.1 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LongCite Llama3.1 8B and how large is it?

LongCite Llama3.1 8B is developed by THUDM, a model with 8b 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 LongCite Llama3.1 8B?

LongCite Llama3.1 8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LongCite Llama3.1 8B by THUDM — VRAM 16.1GB, 128K context

Name: LongCite Llama3.1 8B
Author: THUDM

LongCite Llama3.1 8B is an open-source language model by THUDM. Features: 8b LLM, VRAM: 16.1GB, Context: 128K, LLM Explorer Score: 0.15.

Arxiv:2409.02897 Autotrain compatible Chatglm Custom code Dataset:thudm/longcite-45k En Endpoints compatible Llama Long context Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/THUDM/LongCite-llama3.1-8b

LongCite Llama3.1 8B Parameters and Internals

Model Type

text generation

Use Cases

Applications:

long-context question answering

Additional Notes

The model supports generating fine-grained citations in long-context scenarios.

Supported Languages

en (full), zh (partial)

Training Details

Data Sources:

THUDM/LongCite-45k

Context Length:

128000

Model Architecture:

Llama

Input Output

Input Format:

context and query

Accepted Modalities:

text

Output Format:

structured response with citations

LLM Name	LongCite Llama3.1 8B
Repository 🤗	https://huggingface.co/THUDM/LongCite-llama3.1-8b
Model Size	8b
Required VRAM	16.1 GB
Updated	2025-07-28
Maintainer	THUDM
Model Type	llama
Model Files	3.5 GB: 0-of-5 3.5 GB: 1-of-5 3.5 GB: 2-of-5 3.5 GB: 3-of-5 2.1 GB: 4-of-5
Supported Languages	en zh
Model Architecture	LlamaForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.43.0.dev0
Tokenizer Class	TikTokenizer
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the LongCite Llama3.1 8B 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 LongCite Llama3.1 8B

Best Alternatives	Context / RAM	Downloads	Likes
...otron 8B UltraLong 4M Instruct	4192K / 32.1 GB	1135	125
UltraLong Thinking	4192K / 16.1 GB	2	3
...a 3.1 8B UltraLong 4M Instruct	4192K / 32.1 GB	176	24
...a 3.1 8B UltraLong 2M Instruct	2096K / 32.1 GB	875	9
...otron 8B UltraLong 2M Instruct	2096K / 32.1 GB	124	18
Cthulhu 8B V1.4	1048K / 16.1 GB	10	10
...raLong 1M Instruct Abliterated	1048K / 32.1 GB	4	9
...a 3.1 8B UltraLong 1M Instruct	1048K / 32.1 GB	1387	29
...otron 8B UltraLong 1M Instruct	1048K / 32.1 GB	702	59
...xis Bookwriter Llama3.1 8B Sft	1048K / 16.1 GB	25	4

Note: green Score (e.g. "73.2") means that the model is better than THUDM/LongCite-llama3.1-8b.