Runs On
What it takes to serve english-swahili (77M 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 | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 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 Pius Murimi, published under apache-2.0, revision 3b891fc1b319.
Read Pius Murimi's full model card
license: apache-2.0 language: - en - sw metrics: - bleu base_model: - Helsinki-NLP/opus-mt-en-sw
Configuration
- Architecture
- MarianMTModel
- Context length (tokens)
- 512
- Vocabulary size
- 64,114
- Model type
- marian
Identity and Version
- Repository
- murimixp/english-swahili
- Publisher
- Pius Murimi
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 77M parameters
- Languages
- en, sw
- Revision
- 3b891fc1b319b5864ba45aa2fb94be28343d1702
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
11 files, 311.2 MB in total. The weights are 2 files totalling 308.2 MB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 308.1 MB | bde153c69d08 |
| training_args.bin | Weights | 5.3 KB | 9ad086dc8e06 |
| added_tokens.json | Configuration | 123 B | — |
| config.json | Configuration | 1.3 KB | — |
| generation_config.json | Configuration | 994 B | — |
| README.md | Documentation | 104 B | — |
| source.spm | Other | 790.5 KB | 9129bf81ef9d |
| target.spm | Other | 706.7 KB | 6a0a52318dac |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer_config.json | Tokenizer | 1.6 KB | — |
| vocab.json | Tokenizer | 1.5 MB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 308.2 MB
Released by Pius Murimi through its official repository on Hugging Face. Read the license.
Built From
- Derived from Helsinki-NLP/opus-mt-en-sw
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 308.2 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About english-swahili
How much GPU memory does english-swahili need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (77M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run english-swahili 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 english-swahili commercially?
Yes. english-swahili is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is english-swahili's context length?
512 tokens, from the maximum position embeddings in its published configuration.