What are the hardware requirements for Pandora 13B V1?

Pandora 13B V1 requires approximately 24.9 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Pandora 13B V1 and how large is it?

Pandora 13B V1 is developed by jan-ai, 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 Pandora 13B V1 perform on standard benchmarks?

Pandora 13B V1 has the following published scores: MMLU 63.65. Compare against reference models on this page or on the LLM Explorer leaderboards.

Pandora 13B V1 by jan-ai — VRAM 24.9GB, 32K context

Name: Pandora 13B V1
Author: jan-ai

Pandora 13B V1 is an open-source language model by jan-ai. Features: 13b LLM, VRAM: 24.9GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.11, Arc: 67.1, HellaSwag: 87.5, MMLU: 63.7, GSM8K: 53.

En Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jan-ai/Pandora-13B-v1

Pandora 13B V1 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Applications:

AI chat applications

Primary Use Cases:

Chatbot applications

Additional Notes

Model is created for experimentation with model merging.

Supported Languages

en (Advanced)

Training Details

Data Sources:

viethq188/LeoScorpius-7B-Chat-DPO, GreenNode/GreenNodeLM-7B-v1olet

Methodology:

`passthrough` merge method

Input Output

Input Format:

**ChatML** format

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Use GGUF version to run with Jan.

LLM Name	Pandora 13B V1
Repository 🤗	https://huggingface.co/jan-ai/Pandora-13B-v1
Model Size	13b
Required VRAM	24.9 GB
Updated	2026-08-02
Maintainer	jan-ai
Model Type	mistral
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 5.1 GB: 3-of-3
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Pandora 13B V1 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 Pandora 13B V1

Best Alternatives	Context / RAM	Downloads	Likes
LuminRP 13B 128K V0.5	128K / 25.1 GB	9	2
Breeze 13B 32K Instruct V1.0	32K / 25.6 GB	8	0
Power WizardLM 2 13B	32K / 25 GB	16	2
Mistral V0.3 13B 32K Base V1	32K / 25.2 GB	7	0
Breeze 13B 32K Base V1.0	32K / 25.6 GB	7	0
Pandora V1 13B	32K / 24.9 GB	5	3
BigMistral 13B GLUED	32K / 26.6 GB	15	1
BigMistral 13B	32K / 26.7 GB	1	2
...stral 13B DARE Blended FAILURE	32K / 26.7 GB	6	0
...stral 13B DARE Blended FAILURE	32K / 26.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than jan-ai/Pandora-13B-v1.