Open-weight model
3d-scene-understanding-2023
by Karim Khalil rramirezkyle/3d-scene-understanding-2023
3d-scene-understanding-2023 is an open-weight model from Karim Khalil, released under MIT License. It has 33,088 parameters and a 256-token context. At 16-bit it needs about 0 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
A structured set of research notes on 3D Scene Understanding, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results.
Runs On
What it takes to serve 3d-scene-understanding-2023 (33,088 parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also 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 Oct 18, 2026.
3d-scene-understanding-2023 on every accelerator the SAVRN Index prices, at every precision
Model Card
By Karim Khalil, published under mit, revision cca09975c5f3.
A structured set of research notes on 3D Scene Understanding, 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 task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with analysis.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…
Read Karim Khalil's full model card
Notes on 3D Scene Understanding
Repository summary
A structured set of research notes on 3D Scene Understanding, 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 task-appropriate public benchmarks named in the main note
- reproducibility checks, failure modes, and open questions
- topic-relevant references
How to read this repository
Start with analysis.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
analysis.md— primary artifactREADME.md— this documentation
License
Released under mit. Review the source-data terms separately when this repository is used with external datasets.
Configuration
- Architecture
- CustomResearchModel
- Context length (tokens)
- 256
- Layers
- 3
- Hidden size
- 256
- Feed-forward size
- 1,024
- Attention heads
- 2
- Model type
- transformer
Identity and Version
- Repository
- rramirezkyle/3d-scene-understanding-2023
- Publisher
- Karim Khalil
- 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
- cca09975c5f3df5929c74a2e828a7fbd350e5878
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
6 files, 139.6 KB in total. The weights are 1 file totalling 132.8 KB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 132.8 KB | e3990cda2590 |
| config.json | Configuration | 441 B | — |
| training_args.json | Configuration | 188 B | — |
| README.md | Documentation | 1.5 KB | — |
| analysis.md | Documentation | 3.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 132.8 KB
Released by Karim Khalil through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 132.8 KB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About 3d-scene-understanding-2023
How much GPU memory does 3d-scene-understanding-2023 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 3d-scene-understanding-2023 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 3d-scene-understanding-2023 commercially?
Yes. 3d-scene-understanding-2023 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
What is 3d-scene-understanding-2023's context length?
256 tokens, from the maximum position embeddings in its published configuration.