What are the hardware requirements for Mermaid Llama 3 5B Pruned?

Mermaid Llama 3 5B Pruned requires approximately 10.9 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 Mermaid Llama 3 5B Pruned and how large is it?

Mermaid Llama 3 5B Pruned is developed by TroyDoesAI, a model with 5b 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 Mermaid Llama 3 5B Pruned?

Mermaid Llama 3 5B Pruned is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mermaid Llama 3 5B Pruned by TroyDoesAI — VRAM 10.9GB, 8K context

Name: Mermaid Llama 3 5B Pruned
Author: TroyDoesAI

Mermaid Llama 3 5B Pruned is an open-source language model by TroyDoesAI. Features: 5b LLM, VRAM: 10.9GB, Context: 8K, License: cc-by-4.0, LLM Explorer Score: 0.12.

Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TroyDoesAI/Mermaid-Llama-3-5B-Pruned

Mermaid Llama 3 5B Pruned Parameters and Internals

Model Type

language model

Use Cases

Areas:

Retrieval-Augmented Generation, Q&A systems, Data analysis, Decision-making, Code documentation, Storyboarding, Project planning, Learning Python, Game design

Additional Notes

This model should be treated as an Auto-Complete Model, Do not try talking to it in chat as layers have been pruned and replaced.

Training Details

Data Sources:

800 unique, hand-curated Mermaid Graph examples, 478 complete Python programs

Methodology:

Training includes emergent properties in story-to-flow map translations and step-by-step instruction flow maps.

LLM Name	Mermaid Llama 3 5B Pruned
Repository 🤗	https://huggingface.co/TroyDoesAI/Mermaid-Llama-3-5B-Pruned
Model Size	5b
Required VRAM	10.9 GB
Updated	2026-08-08
Maintainer	TroyDoesAI
Model Type	llama
Model Files	5.0 GB: 1-of-3 4.8 GB: 2-of-3 1.1 GB: 3-of-3
Model Architecture	LlamaForCausalLM
License	cc-by-4.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.39.3
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	float16

Rank the Mermaid Llama 3 5B Pruned 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 Mermaid Llama 3 5B Pruned

Best Alternatives	Context / RAM	Downloads	Likes
Ko Llama 3.1 5B Instruct	128K / 23.4 GB	5	0
Apriel 5B Instruct Llamafied	16K / 9.7 GB	9	4
Llama 3.1 5B Instruct	8K / 10.9 GB	21	1
Triangulum 5B	8K / 10.9 GB	20	2
Triangulum 5B It	8K / 10.9 GB	6	2
Llama 3 5B Sheard	8K / 11.7 GB	8	9
Emhotob 5M	2K / 0 GB	37	0
Ko Llama 230M 0317 5B	2K / 0.6 GB	5	0
Ant 5M	1K / 0 GB	117	2
Linux As A Model 5M	0.5K / 0 GB	15	2

Note: green Score (e.g. "73.2") means that the model is better than TroyDoesAI/Mermaid-Llama-3-5B-Pruned.