GitHub · C++
loopai-hq/pulsar
Pulsar (formerly fastkernel): the fastest inference engine for Qwen3.8-27B and Qwen3.6-35B-A3B on Apple Silicon
- Stars
- 10
- Forks
- 0
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: apple-silicon, gpu-kernels, inference-engine, llm, llm-inference, local-llm, macos, metal, openai-api, qwen
Latest data point: Nov 21, 2026 · 10 stars · 0 forks