Open-weight model · Image and text to text
REX-Qwen3.5-35B-A3B-Cyber-F3
by AI45Research AI45Research/REX-Qwen3.5-35B-A3B-Cyber-F3
REX-Qwen3.5-35B-A3B-Cyber-F3 is an open-weight model for image and text to text from AI45Research, released under Apache License 2.0. It has 37B parameters. At 16-bit it needs about 88.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 7 downloads a month.
Parameters37B
Context—
Weights—
Licenseapache-2.0
AccessOpen weights
Monthly Downloads7
Runs On
What it takes to serve REX-Qwen3.5-35B-A3B-Cyber-F3 (37B 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 | 73.9 GB | 88.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x MI325X $2.00 · 1x MI355X $2.59 |
| 8-bit | 37.0 GB | 44.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 18.5 GB | 22.2 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 20, 2026.
REX-Qwen3.5-35B-A3B-Cyber-F3 on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- AI45Research/REX-Qwen3.5-35B-A3B-Cyber-F3
- Publisher
- AI45Research
- Task
- Image and text to text
- Modality
- Image and text
- Library
- transformers
- Parameters
- 37B parameters
- Languages
- rex
- Revision
- dd0bb380f7d8be64d97cca5cc6a012023ebd4137
- First published
- 2026-10-16
- Last updated
- 2026-10-20
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Download from AI45Research
Released by AI45Research through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3.5-35B-A3B-Base
- Described by arXiv:2610.25791
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 73.9 GB |
| 8-bit | 37.0 GB |
| 4-bit | 18.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About REX-Qwen3.5-35B-A3B-Cyber-F3
How much GPU memory does REX-Qwen3.5-35B-A3B-Cyber-F3 need?
About 88.7 GB at 16-bit and 22.2 GB at 4-bit: the weights (37B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run REX-Qwen3.5-35B-A3B-Cyber-F3 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 REX-Qwen3.5-35B-A3B-Cyber-F3 commercially?
Yes. REX-Qwen3.5-35B-A3B-Cyber-F3 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.
Similar Models
Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. This release delivers substantial upgrades, particularly in For more details, please refer to our blog post Qwen3.6-35B-A3B. Empty cells (--) indicate scores not available or not applicable. For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API. Qwen3.6 can be served via APIs with popular inference frameworks. In…
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL. Empty cells (--) indicate scores not yet available or not applicable. Empty cells (--) indicate scores not…
Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. This release delivers substantial upgrades, particularly in For more details, please refer to our blog post Qwen3.6-35B-A3B. Empty cells (--) indicate scores not available or not applicable. For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API. Qwen3.6 can be served via APIs with popular inference frameworks. In…