LLM EXPLORER 66,613 MODELS INDEXED

Guanaco 65B GGUF by TheBloke

By TheBloke · 226 downloads
HF Repo ↗ Copy URL

Guanaco 65B GGUF is an open-source language model by TheBloke. Features: 65b LLM, VRAM: 27GB, License: other, Quantized, LLM Explorer Score: 0.09.

Base model:quantized:timdettme... Base model:timdettmers/guanaco...   Gguf   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/guanaco-65B-GGUF 

Guanaco 65B GGUF Parameters and Internals

Model Type 
llama
Additional Notes 
The model has been quantized by TheBloke and is available in GGUF format, a new format introduced by the llama.cpp team on August 21st 2023.
Input Output 
Input Format:
### Human: {prompt} ### Assistant:
LLM NameGuanaco 65B GGUF
Repository 🤗https://huggingface.co/TheBloke/guanaco-65B-GGUF 
Model NameGuanaco 65B
Model CreatorTim Dettmers
Base Model(s)  Guanaco 65B   timdettmers/guanaco-65b
Model Size65b
Required VRAM27 GB
Updated2026-07-18
MaintainerTheBloke
Model Typellama
Model Files  27.0 GB   34.6 GB   31.6 GB   28.2 GB   36.8 GB   39.3 GB   36.9 GB   44.9 GB   46.2 GB   44.9 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseother

Best Alternatives to Guanaco 65B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
...en Instruct Human Mix 65B GGUF0K / 27 GB2871
...stage Llama1 65B Instruct GGUF0K / 27 GB11101
LLaMA 65B GGUF0K / 27 GB1575
Airoboros 65B GPT4 2.0 GGML0K / 27.5 GB52
Airoboros 65B GPT4 M2.0 GGML0K / 27.5 GB42
...stage Llama1 65B Instruct GGML0K / 27.5 GB105
LLaMa 65B GGML0K / 27.3 GB625
Medguanaco Lora 65B GPTQ0K / 0.3 GB09
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/guanaco-65B-GGUF.