What are the hardware requirements for Mrcuddle DarkHermes3 Llama3.2 3B Instruct?

Mrcuddle DarkHermes3 Llama3.2 3B Instruct requires approximately 7.2 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 Mrcuddle DarkHermes3 Llama3.2 3B Instruct and how large is it?

Mrcuddle DarkHermes3 Llama3.2 3B Instruct is developed by Nexesenex, 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 Mrcuddle DarkHermes3 Llama3.2 3B Instruct?

Mrcuddle DarkHermes3 Llama3.2 3B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mrcuddle DarkHermes3 Llama3.2 3B Instruct by Nexesenex — VRAM 7.2GB, 128K context

Name: Mrcuddle DarkHermes3 Llama3.2 3B Instruct
Author: Nexesenex

Mrcuddle DarkHermes3 Llama3.2 3B Instruct is an open-source language model by Nexesenex. Features: 3b LLM, VRAM: 7.2GB, Context: 128K, Instruction-Based, LLM Explorer Score: 0.17.

Axolotl Base model:finetune:mrcuddle/d... Base model:mrcuddle/dark-herme... Chat Chatml Conversational Dataset:llamafactory/alpaca en Distillation En Endpoints compatible Finetuned Function calling Generated from trainer Gpt4 Instruct Json mode Llama Llama-3 Region:us Roleplaying Safetensors Sharded Synthetic data Tensorflow

Model Card on HF 🤗: https://huggingface.co/Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct

Mrcuddle DarkHermes3 Llama3.2 3B Instruct Parameters and Internals

LLM Name	Mrcuddle DarkHermes3 Llama3.2 3B Instruct
Repository 🤗	https://huggingface.co/Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct
Base Model(s)	mrcuddle/Dark-Hermes3-Llama3.2-3B mrcuddle/Dark-Hermes3-Llama3.2-3B
Model Size	3b
Required VRAM	7.2 GB
Updated	2026-07-18
Maintainer	Nexesenex
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 2.2 GB: 2-of-2
Supported Languages	en
Model Architecture	LlamaForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.47.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	float32

Rank the Mrcuddle DarkHermes3 Llama3.2 3B Instruct 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 Mrcuddle DarkHermes3 Llama3.2 3B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.2 3B Instruct	128K / 6.5 GB	1829572	2368
Llama 3.2 3B Instruct	128K / 6.5 GB	186207	96
Llama3.2 3B Manumit V1	128K / 6.4 GB	135	0
Llama 3.2 3B Instruct	128K / 6.5 GB	991	9
... V7 SFT 10voicebot Loopcleaned	128K / 6.5 GB	229	0
Llama 3.2 3B RP Toxic Fuse	128K / 6.4 GB	14	2
DeepSeek R1 Distill Llama 3B	128K / 6.5 GB	247	16
Schematron 3B	128K / 6.5 GB	969	336
ReasoningCore 3B T1 1	128K / 6.5 GB	8	1
... 3.2 3B Math Instruct RE1 ORPO	128K / 6.5 GB	48	0

Note: green Score (e.g. "73.2") means that the model is better than Nexesenex/mrcuddle_DarkHermes3-Llama3.2-3B-Instruct.