Open-weight model
roma-student-gold-plus-all-pseudo
by Laith Jaber Laith05/roma-student-gold-plus-all-pseudo
roma-student-gold-plus-all-pseudo is an open-weight model from Laith Jaber. It has 242M parameters. At 16-bit it needs about 0.6 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 roma-student-gold-plus-all-pseudo (242M 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 | 0.5 GB | 0.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.2 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 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.
roma-student-gold-plus-all-pseudo on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- WhisperForConditionalGeneration
- Layers
- 12
- Vocabulary size
- 51,865
- Stored precision
- float32
- Model type
- whisper
Identity and Version
- Repository
- Laith05/roma-student-gold-plus-all-pseudo
- Publisher
- Laith Jaber
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 242M parameters
- Languages
- Not stated by the source
- Revision
- 8a9c5ec3017fd16e89026ae100fe9f7a7ef42fb2
- First published
- 2026-10-06
- Last updated
- 2026-10-07
Files and Weights
12 files, 968.9 MB in total. The weights are 2 files totalling 967.0 MB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 967.0 MB | d7dc8aa5f3bc |
| training_args.bin | Weights | 5.9 KB | fdb1c4bb9b1e |
| added_tokens.json | Configuration | 34.6 KB | — |
| config.json | Configuration | 1.4 KB | — |
| normalizer.json | Configuration | 52.7 KB | — |
| preprocessor_config.json | Configuration | 339 B | — |
| special_tokens_map.json | Configuration | 2.2 KB | — |
| runs/Oct06_15-58-58_f5f8ff244d29/events.out.tfevents.1791302339.f5f8ff244d29.49.0 | Other | 15.0 KB | d1f3927be514 |
| .gitattributes | Repository | 1.5 KB | — |
| merges.txt | Tokenizer | 493.9 KB | — |
| tokenizer_config.json | Tokenizer | 282.7 KB | — |
| vocab.json | Tokenizer | 1.0 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 967.0 MB
Released by Laith Jaber through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 967.0 MB |
| 16-bit | 0.5 GB |
| 8-bit | 0.2 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About roma-student-gold-plus-all-pseudo
How much GPU memory does roma-student-gold-plus-all-pseudo need?
About 0.6 GB at 16-bit and 0.1 GB at 4-bit: the weights (242M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run roma-student-gold-plus-all-pseudo 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.