handwriting-reranker is an open-weight model from Jackson Kahungu. It has 8.3B parameters and a 128,000-token context. At 16-bit it needs about 19.9 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 handwriting-reranker (8.3B 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 | 16.6 GB | 19.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 8.3 GB | 10.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.1 GB | 5.0 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 Sep 24, 2026.
handwriting-reranker on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Qwen2_5_VLForConditionalGeneration
- Context length (tokens)
- 128,000
- Layers
- 28
- Hidden size
- 3,584
- Feed-forward size
- 18,944
- Attention heads
- 28
- Key/value heads
- 4
- Vocabulary size
- 152,064
- Model type
- qwen2_5_vl
Identity and Version
- Repository
- keystats/handwriting-reranker
- Publisher
- Jackson Kahungu
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 8.3B parameters
- Languages
- Not stated by the source
- Revision
- ee43cb2ebec4762c310722f6fa831f68ebdc72aa
- First published
- 2026-09-21
- Last updated
- 2026-09-21
Files and Weights
13 files, 16.6 GB in total. The weights are 4 files totalling 16.6 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00004.safetensors | Weights | 5.0 GB | dbd8c2428ba1 |
| model-00002-of-00004.safetensors | Weights | 4.9 GB | d19a96c79cae |
| model-00003-of-00004.safetensors | Weights | 5.0 GB | 80075a31e0df |
| model-00004-of-00004.safetensors | Weights | 1.7 GB | caa66e61047c |
| config.json | Configuration | 2.4 KB | — |
| generation_config.json | Configuration | 214 B | — |
| model.safetensors.index.json | Configuration | 57.7 KB | — |
| processor_config.json | Configuration | 1.3 KB | — |
| reranker_config.json | Configuration | 715 B | — |
| chat_template.jinja | Other | 1.0 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | f7f96da3a872 |
| tokenizer_config.json | Tokenizer | 786 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 16.6 GB
Released by Jackson Kahungu through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 16.6 GB |
| 16-bit | 16.6 GB |
| 8-bit | 8.3 GB |
| 4-bit | 4.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About handwriting-reranker
How much GPU memory does handwriting-reranker need?
About 19.9 GB at 16-bit and 5 GB at 4-bit: the weights (8.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run handwriting-reranker 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 handwriting-reranker's context length?
128,000 tokens, from the maximum position embeddings in its published configuration.