Open-weight model
beetle-bilingual-l2-50-sequential-33-67-b3-fineweb-2b-est-eng
by Beetle-FineWeb-24B-5 Beetle-FineWeb-24B-5/beetle-bilingual-l2-50-sequential-33-67-b3-fineweb-2b-est-eng
beetle-bilingual-l2-50-sequential-33-67-b3-fineweb-2b-est-eng is an open-weight model from Beetle-FineWeb-24B-5. It has 194M parameters. At 16-bit it needs about 0.5 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 beetle-bilingual-l2-50-sequential-33-67-b3-fineweb-2b-est-eng (194M 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 | 0.4 GB | 0.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.2 GB | 0.2 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.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- PicoDecoderHF
- Vocabulary size
- 50,000
- Stored precision
- float32
- Model type
- pico_decoder
Identity and Version
- Repository
- Beetle-FineWeb-24B-5/beetle-bilingual-l2-50-sequential-33-67-b3-fineweb-2b-est-eng
- Publisher
- Beetle-FineWeb-24B-5
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 194M parameters
- Languages
- Not stated by the source
- Revision
- 16d003b7c5f1faaa60927406c9893b719725a382
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
8 files, 778.9 MB in total. The weights are 1 file totalling 775.2 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 775.2 MB | 2ef62220d8e1 |
| config.json | Configuration | 539 B | — |
| pico_decoder.py | Configuration | 19.7 KB | — |
| special_tokens_map.json | Configuration | 552 B | — |
| training_config.yaml | Configuration | 1.8 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 3.6 MB | — |
| tokenizer_config.json | Tokenizer | 994 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 775.2 MB
Released by Beetle-FineWeb-24B-5 through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 775.2 MB |
| 16-bit | 0.4 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 beetle-bilingual-l2-50-sequential-33-67-b3-fineweb-2b-est-eng
How much GPU memory does beetle-bilingual-l2-50-sequential-33-67-b3-fineweb-2b-est-eng need?
About 0.5 GB at 16-bit and 0.1 GB at 4-bit: the weights (194M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run beetle-bilingual-l2-50-sequential-33-67-b3-fineweb-2b-est-eng 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.