What are the hardware requirements for Medfalcon V2 40B Lora?

Medfalcon V2 40B Lora requires approximately 0.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Medfalcon V2 40B Lora and how large is it?

Medfalcon V2 40B Lora is developed by nmitchko, a model with 40b 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 Medfalcon V2 40B Lora?

Medfalcon V2 40B Lora is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Medfalcon V2 40B Lora by nmitchko — VRAM 0.9GB

Name: Medfalcon V2 40B Lora
Author: nmitchko

Medfalcon V2 40B Lora is an open-source language model by nmitchko. Features: 40b LLM, VRAM: 0.9GB, License: cc-by-nc-4.0, LLM Explorer Score: 0.07.

Arxiv:2106.09685 Adapter Base model:adapter:tiiuae/falc... Base model:tiiuae/falcon-40b En Finetuned Lora Medical Peft Region:us

Model Card on HF 🤗: https://huggingface.co/nmitchko/medfalcon-v2-40b-lora

Medfalcon V2 40B Lora Parameters and Internals

Model Type

LoRA, language model, text generation

Use Cases

Areas:

medical domain tasks

Primary Use Cases:

question-answering, medical dialogue tasks

Limitations:

Do not use to treat patients! Treat AI content as if you wrote it!!!

Additional Notes

Supports 4-bit and 8-bit modes.

Training Details

Data Sources:

medconcat dataset

Data Volume:

100 MiB of raw text

Methodology:

LoRA, specifically QLora

Model Architecture:

LoRA applied to Falcon-40b for medical domain tasks

LLM Name	Medfalcon V2 40B Lora
Repository 🤗	https://huggingface.co/nmitchko/medfalcon-v2-40b-lora
Base Model(s)	Falcon 40B tiiuae/falcon-40b
Model Size	40b
Required VRAM	0.9 GB
Updated	2026-06-23
Maintainer	nmitchko
Model Files	0.9 GB
Supported Languages	en
Model Architecture	Adapter
License	cc-by-nc-4.0
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	dense\|query_key_value\|dense_h_to_4h\|dense_4h_to_h
LoRA Alpha	16
LoRA Dropout	0.05
R Param	64

Rank the Medfalcon V2 40B Lora 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 Medfalcon V2 40B Lora

Best Alternatives	Context / RAM	Downloads	Likes
Falcon 40B Code Alpaca Lora	0K / 0 GB	0	2
Medfalcon 40B Lora	0K / 0.9 GB	6	3
Falcon 40B Chat V0.1	0K / 0 GB	29	38
... 40B Int4 Peft Lora Sfttrainer	0K / 1.8 GB	0	12
Falcon 40B Guanaco Lora	0K / 0.2 GB	0	4
Falcon 40B Qlora Oasst De	0K / 1.8 GB	0	2
...lcon Lora 40b Ckpt 500 Oasst 1	0K / 1.8 GB	0	1
...e WizardLM Uncensored 40B Lora	0K / 0.1 GB	0	1

Note: green Score (e.g. "73.2") means that the model is better than nmitchko/medfalcon-v2-40b-lora.