GitHub · C++
marfrit/arcint
Intel Arc LLM inference server (A770/B60): Qwen hybrids up to Qwen3.8-Flash-Next (512-expert MoE through an expert cache in VRAM and host RAM) on llama.cpp with arcint's own OpenCL kernels, MTP speculation, context checkpoints; image generation, vision, speech in and out
- Stars
- 28
- Forks
- 4
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: intel-arc, llama-cpp, llm-inference, opencl, qwen, speculative-decoding
Latest data point: Nov 21, 2026 · 28 stars · 4 forks