SAVRN
Search Contact SAVRN

Open-weight model

pi05-base-pytorch

by XuJinfan XuJinfan/pi05-base-pytorch

pi05-base-pytorch is an open-weight model from XuJinfan. It has 3.6B parameters. At 16-bit it needs about 8.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.

Parameters3.6B
Context
Weights7.2 GB
License
AccessOpen weights
Monthly Downloads

Runs On

What it takes to serve pi05-base-pytorch (3.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 7.2 GB 8.7 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 3.6 GB 4.3 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 1.8 GB 2.2 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 19, 2026.

pi05-base-pytorch on every accelerator the SAVRN Index prices, at every precision

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
XuJinfan/pi05-base-pytorch
Publisher
XuJinfan
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
3.6B parameters
Languages
Not stated by the source
Revision
a6187bfcb25359f2d1cd459c3ec7f79bc7235fdd
First published
2026-09-19
Last updated
2026-09-19

Files and Weights

3 files, 7.2 GB in total. The weights are 1 file totalling 7.2 GB in safetensors.

Weights1 file · 7.2 GB
Configuration1 file · 149 B
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights7.2 GB 5397c1406326
config.jsonConfiguration149 B
.gitattributesRepository1.5 KB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
7.2 GB
Download from XuJinfan

Released by XuJinfan through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published7.2 GB
16-bit7.2 GB
8-bit3.6 GB
4-bit1.8 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About pi05-base-pytorch

How much GPU memory does pi05-base-pytorch need?

About 8.7 GB at 16-bit and 2.2 GB at 4-bit: the weights (3.6B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run pi05-base-pytorch on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.