What are the hardware requirements for Eeve2.8 Base?

Eeve2.8 Base requires approximately 5.7 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 Eeve2.8 Base and how large is it?

Eeve2.8 Base is developed by kanghokh, a model with 2.8b 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 Eeve2.8 Base?

Eeve2.8 Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Eeve2.8 Base by kanghokh — VRAM 5.7GB, 2K context

Name: Eeve2.8 Base
Author: kanghokh

Eeve2.8 Base is an open-source language model by kanghokh. Features: 2.8b LLM, VRAM: 5.7GB, Context: 2K, Instruction-Based, LLM Explorer Score: 0.13.

Arxiv:1910.09700 Conversational Custom code Endpoints compatible Instruct Phi Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/kanghokh/eeve2.8-base

Eeve2.8 Base Parameters and Internals

LLM Name	Eeve2.8 Base
Repository 🤗	https://huggingface.co/kanghokh/eeve2.8-base
Model Size	2.8b
Required VRAM	5.7 GB
Updated	2026-07-24
Maintainer	kanghokh
Model Type	phi
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 0.7 GB: 2-of-2
Model Architecture	PhiForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.41.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	58944
Torch Data Type	float16

Rank the Eeve2.8 Base 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 Eeve2.8 Base

Best Alternatives	Context / RAM	Downloads	Likes
Phi 2 Instruct Apo	2K / 5.6 GB	8	0
Phi 2 Instruct V0.1	2K / 5.6 GB	8	2
EEVE Korean Instruct 2.8B V1.0	2K / 5.7 GB	2035	28
Att Model	2K / 5.7 GB	8	0
Eeve2.8 Ko	2K / 5.7 GB	5	0
... Instruct 2.8B V1.0 20240430 2	2K / 2.9 GB	7	0
YanoljaNEXT EEVE Instruct 2.8B	2K / 5.7 GB	63	30
Phi 2 Code Instruct	2K / 5.6 GB	7	4
Dolphin 2 6 Phi 2	0K / 5.6 GB	1160	192
Dolphin 2 6 Phi 2	0K / 5.6 GB	801	198

Note: green Score (e.g. "73.2") means that the model is better than kanghokh/eeve2.8-base.