SAVRN
Search Contact SAVRN

Open-weight model

multimodal-reasoning-base

by Jonas W. Schmidt jkschmidt/multimodal-reasoning-base

A structured set of research notes on Multimodal Reasoning, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results.

Parameters33,088
Context128
Weights132.8 KB
Licensecc-by-4.0
AccessOpen weights
Monthly Downloads

Runs On

What it takes to serve multimodal-reasoning-base (33,088 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 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.0 GB 0.0 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

By Jonas W. Schmidt, published under cc-by-4.0, revision 6b50e81f4d43.

A structured set of research notes on Multimodal Reasoning, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as VQAv2, GQA, and NLVR2 - reproducibility checks, failure modes, and open questions - topic-relevant references Start with review.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw logs. The note is intentionally…

Read Jonas W. Schmidt's full model card

Notes on Multimodal Reasoning

Repository summary

A structured set of research notes on Multimodal Reasoning, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results.

What is covered

  • the scope of the research question and likely confounders
  • a proposed comparison with matched baselines
  • concrete evaluation context such as VQAv2, GQA, and NLVR2
  • reproducibility checks, failure modes, and open questions
  • topic-relevant references

How to read this repository

Start with review.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw logs.

Scope and limitations

The note is intentionally exploratory. It does not claim benchmark improvements, completed ablations, released code, or a trained checkpoint. References and proposed datasets provide a starting point for verification rather than evidence that the study has already been run.

Files

  • review.md — primary artifact
  • README.md — this documentation

License

Released under cc-by-4.0. Review the source-data terms separately when this repository is used with external datasets.

Configuration

Architecture
CustomResearchModel
Context length (tokens)
128
Layers
8
Hidden size
256
Feed-forward size
512
Attention heads
2
Model type
transformer

Identity and Version

Repository
jkschmidt/multimodal-reasoning-base
Publisher
Jonas W. Schmidt
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
33,088 parameters
Languages
Not stated by the source
Revision
6b50e81f4d4304b5e88bef0f44e08b9328e9d228
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

6 files, 139.5 KB in total. The weights are 1 file totalling 132.8 KB in safetensors.

Weights1 file · 132.8 KB
Configuration2 files · 628 B
Documentation2 files · 4.6 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights132.8 KB e3990cda2590
config.jsonConfiguration440 B
training_args.jsonConfiguration188 B
README.mdDocumentation1.4 KB
review.mdDocumentation3.1 KB
.gitattributesRepository1.5 KB

License and Download

License
cc-by-4.0
Access
Open weights, no gate
Download size
132.8 KB
Download from Jonas W. Schmidt

Released by Jonas W. Schmidt through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published132.8 KB
16-bit0.0 GB
8-bit0.0 GB
4-bit0.0 GB

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

Questions About multimodal-reasoning-base

How much GPU memory does multimodal-reasoning-base need?

About 0 GB at 16-bit and 0 GB at 4-bit: the weights (33,088 parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run multimodal-reasoning-base 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.

Can I use multimodal-reasoning-base commercially?

Yes. multimodal-reasoning-base is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.

What is multimodal-reasoning-base's context length?

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