PicoPolite240M-base is an open-weight model from Reiwa-AI K.K., released under Gemma Terms of Use. It has 237M parameters and a 51,200-token context. 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.
PicoPolite240M is a small-scale language model created using extremely limited computational resources (a single GPU with 32 GB memory) to research training methods for LLMs and SLMs. We will publish a book detailing the entire learning methodology.
Runs On
What it takes to serve PicoPolite240M-base (237M 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 19, 2026.
PicoPolite240M-base on every accelerator the SAVRN Index prices, at every precision
Model Card
PicoPolite240M is a small-scale language model created using extremely limited computational resources (a single GPU with 32 GB memory) to research training methods for LLMs and SLMs. We will publish a book detailing the entire learning methodology. Furthermore, we will release the complete synthetic dataset created for this purpose. Using the data below, I trained the model for one epoch with a token window of 2000 and fp32 precision; the RoPE θ was set to 3200. Subsequently, using the data below, I trained it for one epoch with a token window of 6400 and bf16 precision; the RoPE θ was set to 10000. Afterward, I applied LongRoPE to extrapolate the token window. This model utilizes google…
Excerpt from the card by Reiwa-AI K.K., licensed gemma.
Configuration
- Architecture
- GptOssForCausalLM
- Context length (tokens)
- 51,200
- Layers
- 16
- Hidden size
- 384
- Feed-forward size
- 1,536
- Attention heads
- 6
- Key/value heads
- 3
- Head dimension
- 64
- Vocabulary size
- 262,144
- Experts
- 1
- Experts active per token
- 1
- Sliding window (tokens)
- 128
- Model type
- gpt_oss
Identity and Version
- Repository
- Reiwa-AI/PicoPolite240M-base
- Publisher
- Reiwa-AI K.K.
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 237M parameters
- Languages
- en, ja
- Revision
- 17a99e3ce792fa049d334bf0419972b41ec83e76
- First published
- 2026-10-03
- Last updated
- 2026-10-03
Files and Weights
8 files, 505.8 MB in total. The weights are 1 file totalling 473.6 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 473.6 MB | ee5032810cc7 |
| config.json | Configuration | 1.9 KB | — |
| generation_config.json | Configuration | 218 B | — |
| README.md | Documentation | 1.9 KB | — |
| chat_template.jinja | Other | 568 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 32.2 MB | cc8d3a0ce364 |
| tokenizer_config.json | Tokenizer | 2.7 KB | — |
License and Download
- License
- gemma
- Access
- Open weights, no gate
- Download size
- 473.6 MB
Released by Reiwa-AI K.K. through its official repository on Hugging Face.
Built From
- Trained on (disclosed) ayousanz/c4-ja-cleaned
- Trained on (disclosed) wikimedia/wikipedia
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 473.6 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 PicoPolite240M-base
How much GPU memory does PicoPolite240M-base need?
About 0.6 GB at 16-bit and 0.1 GB at 4-bit: the weights (237M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run PicoPolite240M-base 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 PicoPolite240M-base commercially?
Yes, with conditions. PicoPolite240M-base is released under Gemma Terms of Use. Gemma models are released under Google's Gemma Terms of Use, which permit commercial use and redistribution subject to the Gemma Prohibited Use Policy, whose restrictions must be passed on to anyone the model is distributed to.
What is PicoPolite240M-base's context length?
51,200 tokens, from the maximum position embeddings in its published configuration.