Open-weight model
olmo-urban-part1
by Compassion aligned machine learning CompassioninMachineLearning/olmo-urban-part1
olmo-urban-part1 is an open-weight model from Compassion aligned machine learning. It has 7.3B parameters and a 65,536-token context. At 16-bit it needs about 17.5 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve olmo-urban-part1 (7.3B 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 | 14.6 GB | 17.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 7.3 GB | 8.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 3.6 GB | 4.4 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 19, 2026.
olmo-urban-part1 on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Olmo3ForCausalLM
- Context length (tokens)
- 65,536
- Layers
- 32
- Hidden size
- 4,096
- Feed-forward size
- 11,008
- Attention heads
- 32
- Key/value heads
- 32
- Vocabulary size
- 100,278
- Sliding window (tokens)
- 4,096
- Model type
- olmo3
Identity and Version
- Repository
- CompassioninMachineLearning/olmo-urban-part1
- Publisher
- Compassion aligned machine learning
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 7.3B parameters
- Languages
- Not stated by the source
- Revision
- fe4319f561ace42f4b47c2bd4bfe02e62ce99070
- First published
- 2026-10-13
- Last updated
- 2026-10-13
Files and Weights
15 files, 14.6 GB in total. The weights are 1 file totalling 14.6 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 14.6 GB | 948f4ca613c5 |
| config.json | Configuration | 1.8 KB | — |
| eval/retention.json | Configuration | 297 B | — |
| eval/summary.json | Configuration | 19.0 KB | — |
| gate/summary.json | Configuration | 2.9 KB | — |
| generation_config.json | Configuration | 39 B | — |
| run_manifest.json | Configuration | 2.4 KB | — |
| trainer_state.json | Configuration | 12.8 KB | — |
| build_logs/finalize_status.txt | Other | 15.8 KB | — |
| chat_template.jinja | Other | 2.6 KB | — |
| eval/harvestbench/2026-10-13T02-38-23-00-00_harvest-contact_gepBXhiq9hsdYzDMeJSheV.eval | Other | 1.4 MB | f047044e6931 |
| eval/tac/2026-10-13T02-27-16-00-00_tac_4Etvc5KA5wMsaaw8rKXUAJ.eval | Other | 663.3 KB | d4a13f0da007 |
| .gitattributes | Repository | 1.7 KB | — |
| tokenizer.json | Tokenizer | 7.1 MB | — |
| tokenizer_config.json | Tokenizer | 377 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 14.6 GB
Released by Compassion aligned machine learning through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 14.6 GB |
| 16-bit | 14.6 GB |
| 8-bit | 7.3 GB |
| 4-bit | 3.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About olmo-urban-part1
How much GPU memory does olmo-urban-part1 need?
About 17.5 GB at 16-bit and 4.4 GB at 4-bit: the weights (7.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run olmo-urban-part1 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 olmo-urban-part1's context length?
65,536 tokens, from the maximum position embeddings in its published configuration.