akan-twi-mms-gentle is an open-weight model from Abdul Rashid Dickson. It has 83M parameters. At 16-bit it needs about 0.2 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 akan-twi-mms-gentle (83M 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 Oct 9, 2026.
akan-twi-mms-gentle on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- VitsModelForPreTraining
- Layers
- 6
- Hidden size
- 192
- Attention heads
- 2
- Vocabulary size
- 30
- Stored precision
- float32
- Model type
- vits
Identity and Version
- Repository
- Dickson32-cell/akan-twi-mms-gentle
- Publisher
- Abdul Rashid Dickson
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 83M parameters
- Languages
- Not stated by the source
- Revision
- b04d529c783121f2f3282c86cf6841dface2b35c
- First published
- 2026-10-09
- Last updated
- 2026-10-09
Files and Weights
11 files, 337.9 MB in total. The weights are 1 file totalling 332.2 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 332.2 MB | e1127b2f2571 |
| added_tokens.json | Configuration | 18 B | — |
| config.json | Configuration | 2.0 KB | — |
| convergence_summary.json | Configuration | 47 B | — |
| special_tokens_map.json | Configuration | 275 B | — |
| loss_curve.png | Other | 255.1 KB | 34cc7144fb26 |
| losses.csv | Other | 130.9 KB | — |
| train_akan.log | Other | 5.3 MB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer_config.json | Tokenizer | 700 B | — |
| vocab.json | Tokenizer | 327 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 332.2 MB
Released by Abdul Rashid Dickson through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 332.2 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 akan-twi-mms-gentle
How much GPU memory does akan-twi-mms-gentle need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (83M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run akan-twi-mms-gentle 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.