What are the hardware requirements for MetaModelv2?

MetaModelv2 requires approximately 21.4 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MetaModelv2 and how large is it?

MetaModelv2 is developed by gagan3012, a model with 10.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does MetaModelv2 perform on standard benchmarks?

MetaModelv2 has the following published scores: MMLU 66.29. Compare against reference models on this page or on the LLM Explorer leaderboards.

MetaModelv2 by gagan3012 — VRAM 21.4GB, 8K context

Name: MetaModelv2
Author: gagan3012

MetaModelv2 is an open-source language model by gagan3012. Features: 10.7b LLM, VRAM: 21.4GB, Context: 8K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.12, Arc: 71.1, HellaSwag: 88.6, MMLU: 66.3, GSM8K: 64.4.

Conversational Endpoints compatible Instruct Llama Merge Metamodelv2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/gagan3012/MetaModelv2

MetaModelv2 Benchmarks

ARC: 71.08 vs 96.7 (so35)^-26.5%

HellaSwag: 88.56 vs 95.3 (gpt4)^-7.1%

MMLU: 66.29 vs 88.3 (so35)^-24.9%

GSM8K: 64.44 vs 96.4 (so35)^-33.2%

LLME Score: 0.1172

^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 🚀

MetaModelv2 Parameters and Internals

Training Details

Data Sources:

VAGOsolutions/SauerkrautLM-SOLAR-Instruct, kyujinpy/Sakura-SOLAR-Instruct

Methodology:

Hybrid and merge of models

LLM Name	MetaModelv2
Repository 🤗	https://huggingface.co/gagan3012/MetaModelv2
Model Size	10.7b
Required VRAM	21.4 GB
Updated	2026-05-08
Maintainer	gagan3012
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-3 9.8 GB: 2-of-3 1.7 GB: 3-of-3
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.35.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Best Alternatives to MetaModelv2

Best Alternatives	Context / RAM	Downloads	Likes
SOLAR 10.7B Instruct V1.0 128K	128K / 21.4 GB	96	3
SOLAR 10.7B V1.0 Instruct 16K	16K / 21.4 GB	63	2
SauerkrautLM SOLAR Instruct	8K / 21.4 GB	234	46
Kazemi 1.2 Solar	8K / 21.4 GB	0	0
SOLAR 10.7B Instruct V1.0	4K / 21.4 GB	62146	654
Somer2	4K / 21.4 GB	11	0
SOLAR 10.7B Instruct V1.0	4K / 21.4 GB	6	0
Solarmer3	4K / 21.4 GB	8	0
Somer	4K / 21.4 GB	9	0
...arbonVillain En 10.7B V2 Slerp	4K / 21.4 GB	12442	0

Note: green Score (e.g. "73.2") means that the model is better than gagan3012/MetaModelv2.

Rank the MetaModelv2 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? 53972 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

MetaModelv2 by gagan3012

» All LLMs » gagan3012 » MetaModelv2 URL Share it on

MetaModelv2 Benchmarks

MetaModelv2 Parameters and Internals

Best Alternatives to MetaModelv2

Rank the MetaModelv2 Capabilities

What open-source LLMs or SLMs are you in search of? 53972 in total.