This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True. BOM.json inventories every release file and EU-BOM.json contains the EU GPAI training-content disclosure mapping.
Open-weight model · Text generation
waldito-smoke-v1-r0002-u0-mdagosta
by Michael D'Agosta mdagosta/waldito-smoke-v1-r0002-u0-mdagosta
waldito-smoke-v1-r0002-u0-mdagosta is an open-weight model for text generation from Michael D'Agosta. It has 820,736 parameters and a 512-token context. At 16-bit it needs about 0 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True.
Parameters820,736
Context512
Weights1.6 MB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve waldito-smoke-v1-r0002-u0-mdagosta (820,736 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 | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 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 7, 2026.
waldito-smoke-v1-r0002-u0-mdagosta on every accelerator the SAVRN Index prices, at every precision
Model Card
This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True. BOM.json inventories every release file and EU-BOM.json contains the EU GPAI training-content disclosure mapping.
Excerpt from the card by Michael D'Agosta.
Configuration
- Architecture
- LlamaForCausalLM
- Context length (tokens)
- 512
- Layers
- 4
- Hidden size
- 128
- Feed-forward size
- 384
- Attention heads
- 4
- Key/value heads
- 2
- Vocabulary size
- 259
- RoPE base
- 10,000
- Stored precision
- bfloat16
- Model type
- llama
Identity and Version
- Repository
- mdagosta/waldito-smoke-v1-r0002-u0-mdagosta
- Publisher
- Michael D'Agosta
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 820,736 parameters
- Languages
- Not stated by the source
- Revision
- 09e1d119c3828f69550c9911339b7ee8155984be
- First published
- 2026-09-30
- Last updated
- 2026-09-30
Files and Weights
12 files, 1.7 MB in total. The weights are 1 file totalling 1.6 MB in safetensors.
Weights1 file · 1.6 MB
Configuration7 files · 13.2 KB
Tokenizer1 file · 712 B
Documentation1 file · 387 B
Other1 file · 381 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.6 MB | 04a0964fea5a |
| BOM.json | Configuration | 2.4 KB | — |
| EU-BOM.json | Configuration | 8.1 KB | — |
| architecture.py | Configuration | 203 B | — |
| config.json | Configuration | 458 B | — |
| generation_config.json | Configuration | 79 B | — |
| special_tokens_map.json | Configuration | 62 B | — |
| tokenization_openwaldo.py | Configuration | 1.9 KB | — |
| README.md | Documentation | 387 B | — |
| chat_template.jinja | Other | 381 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer_config.json | Tokenizer | 712 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.6 MB
Download from Michael D'Agosta
Released by Michael D'Agosta through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.6 MB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About waldito-smoke-v1-r0002-u0-mdagosta
How much GPU memory does waldito-smoke-v1-r0002-u0-mdagosta need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (820,736 parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run waldito-smoke-v1-r0002-u0-mdagosta 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.
What is waldito-smoke-v1-r0002-u0-mdagosta's context length?
512 tokens, from the maximum position embeddings in its published configuration.
Similar Models
This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True. BOM.json inventories every release file and EU-BOM.json contains the EU GPAI training-content disclosure mapping.
This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True. BOM.json inventories every release file and EU-BOM.json contains the EU GPAI training-content disclosure mapping.
This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True. BOM.json inventories every release file and EU-BOM.json contains the EU GPAI training-content disclosure mapping.
This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True. BOM.json inventories every release file and EU-BOM.json contains the EU GPAI training-content disclosure mapping.
This package uses the standard Transformers Llama causal-language-model architecture with OpenWALDO's schema-1 byte tokenizer. Load the tokenizer with trustremotecode=True. BOM.json inventories every release file and EU-BOM.json contains the EU GPAI training-content disclosure mapping.