# yalun753/moe-l2

<https://repo.masters-masters.com/en/repos/yalun753/moe-l2>

[Home](https://repo.masters-masters.com/en) › [yalun753](https://repo.masters-masters.com/en/owners/yalun753) › [moe-l2](https://repo.masters-masters.com/en/repos/yalun753/moe-l2)

yalun753/moe-l2 has 145 stars on GitHub. Its RepoMasters card: Prototype tier. MoE expert offload for low-VRAM GPUs — run 100B+ MoE models (DeepSeek, Qwen…

| Field | Value |
| --- | --- |
| Owner | [yalun753](https://repo.masters-masters.com/en/owners/yalun753) |
| Stars | 145 |
| Forks | 6 |
| Language | [Cuda](https://repo.masters-masters.com/en/languages/cuda) |
| License | Apache-2.0 |
| Created | 2026 |
| Topics | consumer-gpu, deepseek, expert-caching, llama-cpp, llm-inference, moe, vram-optimization |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [yalun753/moe-l2](https://github.com/yalun753/moe-l2) |

## Repository

MoE expert offload for low-VRAM GPUs — run 100B+ MoE models (DeepSeek, Qwen, Mixtral) on 8 GB cards. Expert cache with LRU hot experts, OpenAI-compatible proxy, GGUF multi-shard.

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## Nearby in Cuda

- [lixincn2015/Partial-Order-Pruning · ★ 147 · Cuda · Prototype](https://repo.masters-masters.com/en/repos/lixincn2015/Partial-Order-Pruning)
- [eunomia-bpf/basic-cuda-tutorial · ★ 146 · Cuda · Prototype](https://repo.masters-masters.com/en/repos/eunomia-bpf/basic-cuda-tutorial)
- [Infatoshi/MegaQwen · ★ 145 · Cuda · Prototype](https://repo.masters-masters.com/en/repos/Infatoshi/MegaQwen)
- [enCRYPTON-labs/HEonGPU · ★ 144 · Cuda · Prototype](https://repo.masters-masters.com/en/repos/enCRYPTON-labs/HEonGPU)
- [meder411/PyTorch-EMDLoss · ★ 143 · Cuda · Prototype](https://repo.masters-masters.com/en/repos/meder411/PyTorch-EMDLoss)
- [leimao/CUTLASS-Examples · ★ 143 · Cuda · Prototype](https://repo.masters-masters.com/en/repos/leimao/CUTLASS-Examples)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.