Looped-qwen-pre2 is an open-weight model from Summer Summer, released under Apache License 2.0. It has 989M parameters. At 16-bit it needs about 2.4 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 Looped-qwen-pre2 (989M 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 | 2.0 GB | 2.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.0 GB | 1.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.5 GB | 0.6 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.
Looped-qwen-pre2 on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- LoopedGDNForCausalLM
- Layers
- 24
- Hidden size
- 2,048
- Vocabulary size
- 248,320
- Model type
- looped_gdn
Identity and Version
- Repository
- summerMC/Looped-qwen-pre2
- Publisher
- Summer Summer
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 989M parameters
- Languages
- Not stated by the source
- Revision
- 45b4092d74ad1a8d5b46207b78d3e9b451f020ea
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
11 files, 2.0 GB in total. The weights are 1 file totalling 2.0 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 2.0 GB | b7db8391a6a8 |
| config.json | Configuration | 2.9 KB | — |
| configuration_looped_gdn.py | Configuration | 1.3 KB | — |
| generation_config.json | Configuration | 94 B | — |
| looped_gdn.py | Configuration | 33.9 KB | — |
| modeling_looped_gdn.py | Configuration | 6.0 KB | — |
| README.md | Documentation | 28 B | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | a5cd9732badc |
| tokenizer_config.json | Tokenizer | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 2.0 GB
Released by Summer Summer through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.0 GB |
| 16-bit | 2.0 GB |
| 8-bit | 1.0 GB |
| 4-bit | 0.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Looped-qwen-pre2
How much GPU memory does Looped-qwen-pre2 need?
About 2.4 GB at 16-bit and 0.6 GB at 4-bit: the weights (989M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Looped-qwen-pre2 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 Looped-qwen-pre2 commercially?
Yes. Looped-qwen-pre2 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.