What are the hardware requirements for Merge Aanaphi Phi2 Orage 3B?

Merge Aanaphi Phi2 Orage 3B requires approximately 5.5 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Merge Aanaphi Phi2 Orage 3B and how large is it?

Merge Aanaphi Phi2 Orage 3B is developed by prhegde, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Merge Aanaphi Phi2 Orage 3B perform on standard benchmarks?

Merge Aanaphi Phi2 Orage 3B has the following published scores: MMLU 58.21. Compare against reference models on this page or on the LLM Explorer leaderboards.

Merge Aanaphi Phi2 Orage 3B by prhegde — VRAM 5.5GB, 2K context

Name: Merge Aanaphi Phi2 Orage 3B
Author: prhegde

Merge Aanaphi Phi2 Orage 3B is an open-source language model by prhegde. Features: 3b LLM, VRAM: 5.5GB, Context: 2K, License: mit, Merged, LLM Explorer Score: 0.13, Arc: 63.6, HellaSwag: 77.4, MMLU: 58.2, GSM8K: 61.6.

Merged Model Base model:mobiuslabsgmbh/aana... Base model:rhysjones/phi-2-ora... Conversational Endpoints compatible Phi Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/prhegde/merge-aanaphi-phi2-orage-3b

Merge Aanaphi Phi2 Orage 3B Parameters and Internals

Additional Notes

This model is a merge of two models: rhysjones/phi-2-orange-v2 and mobiuslabsgmbh/aanaphi2-v0.1 using mergekit.

Training Details

Methodology:

SLERP merge method used for merging models.

LLM Name	Merge Aanaphi Phi2 Orage 3B
Repository 🤗	https://huggingface.co/prhegde/merge-aanaphi-phi2-orage-3b
Base Model(s)	Phi 2 Orange V2 mobiuslabsgmbh/aanaphi2-v0.1 rhysjones/phi-2-orange-v2 mobiuslabsgmbh/aanaphi2-v0.1
Merged Model	Yes
Model Size	3b
Required VRAM	5.5 GB
Updated	2026-08-04
Maintainer	prhegde
Model Type	phi
Model Files	1.9 GB: 1-of-3 2.0 GB: 2-of-3 1.6 GB: 3-of-3
Model Architecture	PhiForCausalLM
License	mit
Context Length	2048
Model Max Length	2048
Transformers Version	4.38.2
Tokenizer Class	CodeGenTokenizer
Padding Token	[PAD]
Vocabulary Size	51200
Torch Data Type	bfloat16

Rank the Merge Aanaphi Phi2 Orage 3B 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 Merge Aanaphi Phi2 Orage 3B

Best Alternatives	Context / RAM	Downloads	Likes
MFANN Phigments Slerp 3B	2K / 5.6 GB	7	0
...ed Merge Aanaphi Phi2 Orage 3B	2K / 11.1 GB	5	0
Test 3B Runpod 4	2K / 5.5 GB	17	1
Seldonium 3B	0K / 5.6 GB	10	0
Airophi 3B	0K / 11.1 GB	8	1

Note: green Score (e.g. "73.2") means that the model is better than prhegde/merge-aanaphi-phi2-orage-3b.