What are the hardware requirements for Discord Micae Hermes 3 3B?

Discord Micae Hermes 3 3B requires approximately 6.5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Discord Micae Hermes 3 3B and how large is it?

Discord Micae Hermes 3 3B is developed by mookiezi, a model with 3b 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 Discord Micae Hermes 3 3B?

Discord Micae Hermes 3 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Discord Micae Hermes 3 3B by mookiezi — VRAM 6.5GB, 128K context

Name: Discord Micae Hermes 3 3B
Author: mookiezi

Discord Micae Hermes 3 3B is an open-source language model by mookiezi. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, License: llama3, Merged, LLM Explorer Score: 0.21.

Merged Model Arxiv:2408.11857 3b-parameters Autotrain compatible Base model:finetune:nousresear... Base model:nousresearch/hermes... Chat Chatml Conversational Conversational-ai Dataset:mookiezi/discord-openm... Discord-dataset Endpoints compatible Finetuned Hermes Instruct Llama Llama-3 Open-weights Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mookiezi/Discord-Micae-Hermes-3-3B

Discord Micae Hermes 3 3B Parameters and Internals

LLM Name	Discord Micae Hermes 3 3B
Repository 🤗	https://huggingface.co/mookiezi/Discord-Micae-Hermes-3-3B
Base Model(s)	NousResearch/Hermes-3-Llama-3.2-3B NousResearch/Hermes-3-Llama-3.2-3B
Merged Model	Yes
Model Size	3b
Required VRAM	6.5 GB
Updated	2025-09-23
Maintainer	mookiezi
Model Type	llama
Model Files	5.0 GB: 1-of-2 1.5 GB: 2-of-2
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	131072
Model Max Length	131072
Transformers Version	4.53.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	float16

Rank the Discord Micae Hermes 3 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 Discord Micae Hermes 3 3B

Best Alternatives	Context / RAM	Downloads	Likes
Nanbeige4.1 3B	256K / 7.9 GB	20875	1161
Nanbeige4.1 3B Heretic	256K / 7.9 GB	149	50
Nanbeige4.1 3B Bf16	256K / 7.9 GB	47	3
Nanbeige4.1 3B Heretic Mxfp4	256K / 7.9 GB	34	2
Nanbeige4.1 3B Heretic	256K / 7.9 GB	14	1
Nanbeige4.1 3B Heretic	256K / 7.9 GB	7	0
ISA 03 Mini 3B Hybrid Preview	256K / 6.5 GB	4	4
ToolMind Web 3B	192K / 7.9 GB	156	28
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368
G9v3 3B	128K / 6 GB	2670	31

Note: green Score (e.g. "73.2") means that the model is better than mookiezi/Discord-Micae-Hermes-3-3B.