Open-weight model
Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers
by Valerio 43ntropy/Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers
Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers is an open-weight model from Valerio, released under MIT License. It has 14.3B parameters. At 16-bit it needs about 34.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Wan 2.2 T2V model merged with LoRA UnifiedReward Flex. BF16 quantization with excluded layers.
Runs On
What it takes to serve Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers (14.3B 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 | 28.6 GB | 34.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 14.3 GB | 17.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 7.1 GB | 8.6 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
By Valerio, published under mit, revision 077a380cc09c.
Wan 2.2 T2V model merged with LoRA UnifiedReward Flex. BF16 quantization with excluded layers.
Read Valerio's full model card
Wan 2.2 T2V model merged with LoRA UnifiedReward Flex.
BF16 quantization with excluded layers.
Identity and Version
- Repository
- 43ntropy/Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers
- Publisher
- Valerio
- Task
- Not stated by the source
- Modality
- Other
- Library
- diffusers
- Parameters
- 14.3B parameters
- Languages
- Not stated by the source
- Revision
- 077a380cc09c507cba4e40aaeb6f178ddbb234b3
- First published
- 2026-09-25
- Last updated
- 2026-09-25
Files and Weights
6 files, 57.9 GB in total. The weights are 2 files totalling 57.9 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| transformer/diffusion_pytorch_model.safetensors | Weights | 29.0 GB | 7d2114310146 |
| transformer_2/diffusion_pytorch_model.safetensors | Weights | 29.0 GB | c9a4b05f0a07 |
| transformer/config.json | Configuration | 411 B | — |
| transformer_2/config.json | Configuration | 411 B | — |
| README.md | Documentation | 207 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 57.9 GB
Released by Valerio through its official repository on Hugging Face. Read the license.
Built From
- Derived from CodeGoat24/Wan2.2-T2V-A14B-UnifiedReward-Flex-lora
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 57.9 GB |
| 16-bit | 28.6 GB |
| 8-bit | 14.3 GB |
| 4-bit | 7.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers
How much GPU memory does Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers need?
About 34.3 GB at 16-bit and 8.6 GB at 4-bit: the weights (14.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers 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 Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers commercially?
Yes. Wan2.2-T2V-A14B-BF16-UnifiedReward-Flex-Diffusers is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.