Open-weight model
arabic-legalAI-ocr-merged-checkpoint-1300
by Ayman nadanedon/arabic-legalAI-ocr-merged-checkpoint-1300
arabic-legalAI-ocr-merged-checkpoint-1300 is an open-weight model from Ayman. It has 4.3B parameters and a 131,072-token context. At 16-bit it needs about 10.3 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 arabic-legalAI-ocr-merged-checkpoint-1300 (4.3B 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 | 8.6 GB | 10.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.3 GB | 5.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.2 GB | 2.6 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
- Gemma3ForConditionalGeneration
- Context length (tokens)
- 131,072
- Layers
- 34
- Hidden size
- 2,560
- Feed-forward size
- 10,240
- Attention heads
- 8
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 262,208
- Sliding window (tokens)
- 1,024
- Model type
- gemma3
Identity and Version
- Repository
- nadanedon/arabic-legalAI-ocr-merged-checkpoint-1300
- Publisher
- Ayman
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 4.3B parameters
- Languages
- Not stated by the source
- Revision
- 422d634a3128eb321bb55655c1bc6cc8316cf3c7
- First published
- 2026-10-05
- Last updated
- 2026-10-05
Files and Weights
8 files, 8.6 GB in total. The weights are 1 file totalling 8.6 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 8.6 GB | f3a44a2bc0d7 |
| config.json | Configuration | 2.8 KB | — |
| generation_config.json | Configuration | 210 B | — |
| processor_config.json | Configuration | 519 B | — |
| chat_template.jinja | Other | 1.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 33.4 MB | daab2354f8a7 |
| tokenizer_config.json | Tokenizer | 745 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 8.6 GB
Released by Ayman through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 8.6 GB |
| 16-bit | 8.6 GB |
| 8-bit | 4.3 GB |
| 4-bit | 2.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About arabic-legalAI-ocr-merged-checkpoint-1300
How much GPU memory does arabic-legalAI-ocr-merged-checkpoint-1300 need?
About 10.3 GB at 16-bit and 2.6 GB at 4-bit: the weights (4.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run arabic-legalAI-ocr-merged-checkpoint-1300 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 arabic-legalAI-ocr-merged-checkpoint-1300's context length?
131,072 tokens, from the maximum position embeddings in its published configuration.