RuleGuidedQwen is an open-weight model from Ivan Ojok, released under Apache License 2.0. It has 494M parameters and a 32,768-token context. At 16-bit it needs about 1.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
This model is a LoRA finetuned Qwen model that employs production rules to ensure strictt rule compliance with Grade2 Braille rules and outperforms a neural-only model on UEB compliance metrics like compliance, capitalization, punctuation, numeric, and OOV…
Runs On
What it takes to serve RuleGuidedQwen (494M 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 | 1.0 GB | 1.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.5 GB | 0.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.3 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.
RuleGuidedQwen on every accelerator the SAVRN Index prices, at every precision
Model Card
By Ivan Ojok, published under apache-2.0, revision 65665fa46447.
This model is a LoRA finetuned Qwen model that employs production rules to ensure strictt rule compliance with Grade2 Braille rules and outperforms a neural-only model on UEB compliance metrics like compliance, capitalization, punctuation, numeric, and OOV accuracy. These individual metrics form the model's recall. The precision score of the model (accounts for character insertions in the outputs differing from references) is also way better than the stand-alone neural model.
Read Ivan Ojok's full model card
This model is a LoRA finetuned Qwen model that employs production rules to ensure strictt rule compliance with Grade2 Braille rules and outperforms a neural-only model on UEB compliance metrics like compliance, capitalization, punctuation, numeric, and OOV accuracy. These individual metrics form the model's recall. The precision score of the model (accounts for character insertions in the outputs differing from references) is also way better than the stand-alone neural model.
Configuration
- Architecture
- RuleGuidedBrailleQwen
- Context length (tokens)
- 32,768
- Layers
- 24
- Hidden size
- 896
- Feed-forward size
- 4,864
- Attention heads
- 14
- Key/value heads
- 2
- Vocabulary size
- 151,936
- Model type
- rule_guided_braille_qwen
Identity and Version
- Repository
- IvanOjok/RuleGuidedQwen
- Publisher
- Ivan Ojok
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 494M parameters
- Languages
- Not stated by the source
- Revision
- 65665fa464473c1f4d3fa641775471a5c749b44d
- First published
- 2026-09-28
- Last updated
- 2026-09-28
Files and Weights
6 files, 988.1 MB in total. The weights are 1 file totalling 988.1 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 988.1 MB | fdf756fa7fcb |
| config.json | Configuration | 5.4 KB | — |
| generation_config.json | Configuration | 242 B | — |
| modeling_rule_guided_qwen.py | Configuration | 10.9 KB | — |
| README.md | Documentation | 509 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 988.1 MB
Released by Ivan Ojok through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 988.1 MB |
| 16-bit | 1.0 GB |
| 8-bit | 0.5 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About RuleGuidedQwen
How much GPU memory does RuleGuidedQwen need?
About 1.2 GB at 16-bit and 0.3 GB at 4-bit: the weights (494M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run RuleGuidedQwen 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 RuleGuidedQwen commercially?
Yes. RuleGuidedQwen is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is RuleGuidedQwen's context length?
32,768 tokens, from the maximum position embeddings in its published configuration.