AlphaUncommon
Indras-Mirror/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…
- Owner
- Indras-Mirror (personal account)
- Stars
- Stars: 449
- Forks
- Forks: 56
- Language
- C++
- License
- MIT
- Created
- 2026
- Topics
- cudadeepseekdeepseek-v4ggufglmllm-inferencelocal-llmmixture-of-expertsmoeoffloading
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in C++
All C++ repos- Zwandiboss08/pose_cameraStars: 449C++Alpha
- OpenDriveLab/kai0Stars: 449C++Alpha
- 25H/MayeNanoStars: 449C++Alpha
- TankOs/SFGUIStars: 449C++Alpha
- fast-pack/SIMDCompressionAndIntersectionStars: 449C++Alpha
- meganz/mingw-std-threadsStars: 449C++Alpha