What are the hardware requirements for Gunny?

Gunny 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 Gunny and how large is it?

Gunny is developed by bfuzzy1, 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 Gunny?

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

Gunny by bfuzzy1 — VRAM 6.5GB, 128K context

Name: Gunny
Author: bfuzzy1

Gunny is an open-source language model by bfuzzy1. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, Quantized, Instruction-Based, LLM Explorer Score: 0.21.

Conversational Dataset:bfuzzy1/gunny v2 solo ... Dataset:bfuzzy1/gunny x Endpoints compatible Gguf Instruct Llama Q4 Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/bfuzzy1/Gunny

Gunny Parameters and Internals

LLM Name	Gunny
Repository 🤗	https://huggingface.co/bfuzzy1/Gunny
Model Size	3b
Required VRAM	6.5 GB
Updated	2026-07-23
Maintainer	bfuzzy1
Model Type	llama
Instruction-Based	Yes
Model Files	2.0 GB 5.0 GB: 1-of-2 1.5 GB: 2-of-2
GGUF Quantization	Yes
Quantization Type	q4\|gguf\|q4_k
Model Architecture	LlamaForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.46.1
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	float16

Rank the Gunny 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 Gunny

Best Alternatives	Context / RAM	Downloads	Likes
KielMind Lite	128K / 2 GB	1712	1
KielMind Pro	128K / 2 GB	46	1
Llama 3.2 MEDIT 3B O1	128K / 7.2 GB	81	13
ReWiz Llama 3.2 3B	128K / 6.5 GB	341	3
Llama 3.2 3B Instruct GGUF	128K / 0.9 GB	27639	72
Teuta	128K / 6.5 GB	1153	2
Leyes Ecuador 20250825 200051	128K / 6.5 GB	35	0
Automotive 20250816 105217	128K / 6.5 GB	44	0
Llama 3.2 3B COT	128K / 6.5 GB	40	2
Llama3 Finetuned Id 16bit	128K / 6.5 GB	652	0

Note: green Score (e.g. "73.2") means that the model is better than bfuzzy1/Gunny.