What are the hardware requirements for Autotrain Umberto Proclama?

Autotrain Umberto Proclama requires approximately 0.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Autotrain Umberto Proclama and how large is it?

Autotrain Umberto Proclama is developed by Proclama. 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 Autotrain Umberto Proclama?

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

Autotrain Umberto Proclama by Proclama — VRAM 0.9GB

Name: Autotrain Umberto Proclama
Author: Proclama

Autotrain Umberto Proclama is an open-source language model by Proclama. Features: LLM, VRAM: 0.9GB, License: other, Instruction-Based, LLM Explorer Score: 0.13.

Autotrain Base model:finetune:microsoft/... Base model:microsoft/phi-3-min... Conversational Dataset:proclama/umberto Endpoints compatible Instruct Lora Peft Region:us Safetensors Tensorboard

Model Card on HF 🤗: https://huggingface.co/Proclama/autotrain-umberto-proclama

Autotrain Umberto Proclama Parameters and Internals

Model Type

text-generation

Additional Notes

Model trained using AutoTrain.

Input Output

Input Format:

Prompt content: "hi"

Accepted Modalities:

text

Output Format:

"Hello! How can I assist you today?"

LLM Name	Autotrain Umberto Proclama
Repository 🤗	https://huggingface.co/Proclama/autotrain-umberto-proclama
Base Model(s)	Phi 3 Mini 4K Instruct microsoft/Phi-3-mini-4k-instruct
Required VRAM	0.9 GB
Updated	2026-08-08
Maintainer	Proclama
Instruction-Based	Yes
Model Files	0.9 GB 0.0 GB
Model Architecture	AutoModel
License	other
Model Max Length	2048
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	o_proj\|down_proj\|qkv_proj\|gate_up_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16

Rank the Autotrain Umberto Proclama 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 Autotrain Umberto Proclama

Best Alternatives	Context / RAM	Downloads	Likes
...l 8x7B Instruct V0.1 Llamafile	0K / GB	7076	18
Mamba Python	0K / 2 GB	13	0
...l 8x7B Instruct V0.1 Llamafile	0K / GB	3180	18
...hi 3 Mini 4K Instruct Ct2 Int8	0K / 3.8 GB	8	1
CSUMLM	0K / GB	13	1
...hin 2.5 Mixtral 8x7b Llamafile	0K / GB	117	4
Instruct GPT J	0K / 0 GB	0	26
Vigogne Bloom 7b1 Instruct	0K / 0.1 GB	0	4
...a Instruction Fine Tune French	0K / 0 GB	0	4
MiniMaid L3	0K / 0 GB	9	2

Note: green Score (e.g. "73.2") means that the model is better than Proclama/autotrain-umberto-proclama.