Strata-DualGPU
Strata for a PC with two NVIDIA GPUs and 32 GB of RAM: the low-RAM mode on a layer split, both cards working at the same time. 143 tok/s on an RTX 5080 + 4060 Ti.
- cuda
- inference
- llm
- local-llm
- mixture-of-experts
- multi-gpu
- qwen
- speculative-decoding
- Stars
- 81
- Forks
- 5
- + today
- +1
- Created
- 28d
Ranking data as of October 31, 2026 (UTC).
Star History
Today, hour by hour
01
Overview
Strata for a PC with two NVIDIA GPUs and 32 GB of RAM: the low-RAM mode on a layer split, both cards working at the same time. 143 tok/s on an RTX 5080 + 4060 Ti. It ranks #2215 on GitTiger, gaining +1 star on October 31, 2026 (UTC).
The project is written in C++ and has 5 forks. It was created 28d ago.
Installation
git clone https://github.com/Hardin22/Strata-DualGPU.git
cd Strata-DualGPU
# see README for setup