Splash 1.1.0 released, GGUF quants support, MLX import and more
Summary
Splash 1.1.0 has been released with GGUF quantization support, MLX import, and optimized kernels for Apple Silicon, enabling efficient local AI inference at high speeds.
Similar Articles
@jianchen1799: Local models can now handle agentic workloads. Local inference engines need to catch up. Today we’re releasing Splash: …
Inco AI releases Splash, an open-source inference engine optimized for Apple silicon, claiming up to 3× faster decode speeds for local model serving, enabling agentic workloads on devices like M5 Max MacBook Pro.
Splash fork optimised for M5 Max: ~1.5× faster (1.25× single request)
Splish is an unofficial fork of Splash that optimizes Metal kernels for Apple M5 Max chips, delivering up to 1.5× faster AI inference speeds for models like Qwen3.8-27B without compromising quality.
[Splash Engine] Qwen3.8-27B in native 8-bit at 37–55 tok/s on Apple Silicon: Extending Splash to Q8, 256k context scaling, and the "Reasoning Cliff"
Extended Splash Engine to support native 8-bit Qwen3.8-27B on Apple Silicon, achieving 37-55 tok/s without quantization degradation and scaling up to 256k context.
KFlash: Benchmarks of newly released versions of Apple Silicon optimized engines: 1.4.0 Splash (DFlash2 ~ 50 tok/s) vs 0.2 Kapitsa (KFlash ~65 tok/s), MLX(MTP) & more on Qwen 3.8 27b/4b/35b 4Q on Macbook Pro M4 Pro 48 GB 2024, 48GB & Macbook Pro M1 Pro 16GB 2021
Nace.AI's Kapitsa 0.2 ships KFlash, a best-first tree-based speculative decoding method for Apple Silicon, benchmarked against Splash 1.4.0's DFlash2, mlx-serve, Ollama, llama.cpp and others on Qwen models across M4 Pro and M1 Pro MacBooks, showing top decode throughput (~65-201 tok/s).
@jundotkim: oMLX 0.3.9.dev2 released. Highlights: - Gemma 4 MTP on the vision path (thanks to @Prince_Canuma's mlx-vlm). Image+text…
oMLX 0.3.9.dev2 is released with improved Gemma 4 support, DFlash engine integration, and ParoQuant capabilities for local LLM inference on Apple Silicon.