What are the hardware requirements for Medguanaco Lora 65B GPTQ?

Medguanaco Lora 65B GPTQ requires approximately 0.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Medguanaco Lora 65B GPTQ and how large is it?

Medguanaco Lora 65B GPTQ is developed by nmitchko, a model with 65b 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 Medguanaco Lora 65B GPTQ?

Medguanaco Lora 65B GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Medguanaco Lora 65B GPTQ by nmitchko — VRAM 0.3GB

Name: Medguanaco Lora 65B GPTQ
Author: nmitchko

Medguanaco Lora 65B GPTQ is an open-source language model by nmitchko. Features: 65b LLM, VRAM: 0.3GB, License: cc, Quantized, LLM Explorer Score: 0.07.

Arxiv:2106.09685 Arxiv:2303.14070 En Endpoints compatible Gptq Lora Medical Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/nmitchko/medguanaco-lora-65b-GPTQ

Medguanaco Lora 65B GPTQ Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

medical domain

Primary Use Cases:

question-answering, medical dialogue tasks

Limitations:

May not perform effectively outside the medical domain, Primarily targets the knowledge level of medical students, Not tested in real-world applications, Not a substitute for a doctor's opinion

Considerations:

Must be treated as a research tool only

Additional Notes

The training data is still under development, with approximately 70% of question-answer pairs believed to be factually correct.

Supported Languages

en (English)

Training Details

Data Sources:

Anki flashcards, Wikidoc, StackExchange, ChatDoctor

Data Volume:

Multiple datasets with varying numbers of question-answer pairs

Methodology:

Used LoRA and quantization techniques

Model Architecture:

65B parameters, fine-tuned for medical domain tasks

LLM Name	Medguanaco Lora 65B GPTQ
Repository 🤗	https://huggingface.co/nmitchko/medguanaco-lora-65b-GPTQ
Model Size	65b
Required VRAM	0.3 GB
Updated	2026-08-05
Maintainer	nmitchko
Model Files	0.3 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Model Architecture	AutoModel
License	cc
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|v_proj
LoRA Alpha	64
LoRA Dropout	0.05
R Param	32

Rank the Medguanaco Lora 65B GPTQ 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 Medguanaco Lora 65B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
...en Instruct Human Mix 65B GGUF	0K / 27 GB	287	1
...stage Llama1 65B Instruct GGUF	0K / 27 GB	1110	1
Guanaco 65B GGUF	0K / 27 GB	226	5
LLaMA 65B GGUF	0K / 27 GB	157	5
Airoboros 65B GPT4 2.0 GGML	0K / 27.5 GB	5	2
Airoboros 65B GPT4 M2.0 GGML	0K / 27.5 GB	4	2
...stage Llama1 65B Instruct GGML	0K / 27.5 GB	10	5
LLaMa 65B GGML	0K / 27.3 GB	6	25

Note: green Score (e.g. "73.2") means that the model is better than nmitchko/medguanaco-lora-65b-GPTQ.