What are the hardware requirements for Lumina 2?

Lumina 2 requires approximately 37.1 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 Lumina 2 and how large is it?

Lumina 2 is developed by Ppoyaa, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Lumina 2 perform on standard benchmarks?

Lumina 2 has the following published scores: MMLU 64.05. Compare against reference models on this page or on the LLM Explorer leaderboards.

Lumina 2 by Ppoyaa — VRAM 37.1GB, 32K context

Name: Lumina 2
Author: Ppoyaa

Lumina 2 is an open-source language model by Ppoyaa. Features: 7b LLM, VRAM: 37.1GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.14, Arc: 66.2, HellaSwag: 86, MMLU: 64.1, GSM8K: 58.4.

Conversational Endpoints compatible Frankenmoe Lazymergekit Merge Mergekit Mixtral Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Ppoyaa/Lumina-2

Lumina 2 Benchmarks

ARC: 66.21 vs 96.7 (so35)^-31.5%

HellaSwag: 86.03 vs 95.3 (gpt4)^-9.7%

MMLU: 64.05 vs 88.3 (so35)^-27.5%

GSM8K: 58.38 vs 96.4 (so35)^-39.4%

LLME Score: 0.13616

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

Lumina 2 Parameters and Internals

Model Type

generative, Sparse Mixture of Experts (MoE)

LLM Name	Lumina 2
Repository 🤗	https://huggingface.co/Ppoyaa/Lumina-2
Model Size	7b
Required VRAM	37.1 GB
Updated	2026-05-03
Maintainer	Ppoyaa
Model Type	mixtral
Model Files	1.9 GB: 1-of-19 2.0 GB: 2-of-19 2.0 GB: 3-of-19 2.0 GB: 4-of-19 2.0 GB: 5-of-19 2.0 GB: 6-of-19 2.0 GB: 7-of-19 2.0 GB: 8-of-19 2.0 GB: 9-of-19 2.0 GB: 10-of-19 2.0 GB: 11-of-19 2.0 GB: 12-of-19 2.0 GB: 13-of-19 2.0 GB: 14-of-19 2.0 GB: 15-of-19 2.0 GB: 16-of-19 2.0 GB: 17-of-19 2.0 GB: 18-of-19 1.2 GB: 19-of-19
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Best Alternatives to Lumina 2

Best Alternatives	Context / RAM	Downloads	Likes
Multimaster 7B V6	32K / 142.5 GB	8380	1
Mini Mixtral V0.2	32K / 25.8 GB	3061	4
MultiverseBuddy 15B MoE	32K / 25.8 GB	9	0
OpenMistral MoE	32K / 48.3 GB	1218	0
Laserxtral	32K / 48.3 GB	810	78
Rawr	32K / 93.5 GB	1302	0
RogerWizard 12B MoE	32K / 25.8 GB	4	1
Merged Model MoE	32K / 53.3 GB	4	1
StarlingMaths 12B MoE	32K / 25.8 GB	5	0
Lumina 3	32K / 37.1 GB	55	0

Note: green Score (e.g. "73.2") means that the model is better than Ppoyaa/Lumina-2.

Rank the Lumina 2 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53885 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Lumina 2 by Ppoyaa

» All LLMs » Ppoyaa » Lumina 2 URL Share it on

Lumina 2 Benchmarks

Lumina 2 Parameters and Internals

Best Alternatives to Lumina 2

Rank the Lumina 2 Capabilities

What open-source LLMs or SLMs are you in search of? 53885 in total.