PrototypeCommon
JakeATX/llamAmpere
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx
- Owner
- JakeATX (personal account)
- Stars
- Stars: 214
- Forks
- Forks: 30
- Language
- C++
- License
- MIT
- Created
- 2026
- Topics
- ampereconsumer-gpucudaggmlggufkv-cache-quantizationllama-cppllmllm-inferencelocal-llm
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in C++
All C++ repos- hwbp/CLR-UnhookStars: 214C++Prototype
- FinalScave/SweetEditorStars: 214C++Prototype
- samine825/Hypr3DStars: 214C++Prototype
- wang-bin/qdevicewatcherStars: 214C++Prototype
- dubey/weaverStars: 214C++Prototype
- CroatiaControlLtd/asterixStars: 214C++Prototype