SAVRN
Search Contact SAVRN

Open-weight model

math_memorization_seen

by Minju Gwak talzoomanzoo/math_memorization_seen

Parameters3.1B
Context32,768
Weights6.2 GB
License
AccessOpen weights
Monthly Downloads

Runs On

What it takes to serve math_memorization_seen (3.1B 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 6.2 GB 7.4 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 3.1 GB 3.7 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 1.5 GB 1.9 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 18, 2026.

Model Card

The publisher has not written a card for this model.

Configuration

Architecture
Qwen2ForCausalLM
Context length (tokens)
32,768
Layers
36
Hidden size
2,048
Feed-forward size
11,008
Attention heads
16
Key/value heads
2
Vocabulary size
151,936
Model type
qwen2

Identity and Version

Repository
talzoomanzoo/math_memorization_seen
Publisher
Minju Gwak
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
3.1B parameters
Languages
Not stated by the source
Revision
4838efaeb8977b798d15ad0a4b7b57bf93c38cb5
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

7 files, 6.2 GB in total. The weights are 1 file totalling 6.2 GB in safetensors.

Weights1 file · 6.2 GB
Configuration2 files · 1.8 KB
Tokenizer2 files · 11.4 MB
Other1 file · 2.5 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights6.2 GB 84602f3d0678
config.jsonConfiguration1.6 KB
generation_config.jsonConfiguration243 B
chat_template.jinjaOther2.5 KB
.gitattributesRepository1.6 KB
tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
tokenizer_config.jsonTokenizer693 B

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
6.2 GB
Download from Minju Gwak

Released by Minju Gwak through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published6.2 GB
16-bit6.2 GB
8-bit3.1 GB
4-bit1.5 GB

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

Questions About math_memorization_seen

How much GPU memory does math_memorization_seen need?

About 7.4 GB at 16-bit and 1.9 GB at 4-bit: the weights (3.1B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run math_memorization_seen 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.

What is math_memorization_seen's context length?

32,768 tokens, from the maximum position embeddings in its published configuration.