Xolotl
Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic
- cuda
- deepseek
- deepseek-v4
- gguf
- glm
- llm-inference
- local-llm
- mixture-of-experts
- moe
- offloading
- qwen
- rtx-4090
- strata
- Stars
- 419
- Forks
- 52
- + today
- +1
- Created
- 25d
Ranking data as of October 31, 2026 (UTC).
Star History
Today, hour by hour
Overview
Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic It ranks #2360 on GitTiger, gaining +1 star on October 31, 2026 (UTC).
The project is written in C++ and has 52 forks. It was created 25d ago.
git clone https://github.com/Indras-Mirror/Xolotl.git
cd Xolotl
# see README for setup