This is your work, valued

Earth

Anemll

Elite
@Anemll

ANEMLL (pronounced like "animal") Artificial Neural Engine Machine Learning Library, Open Source Project

Anemll. Artificial Neural Engine Machine Learning Library

1.6k

flash-moe. Objective-C

217

anemll-flash-llama.cpp. Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork

117

mlx-rdma. experiments with MLX

68

anemll-bench. Python

52

Flash-iOS. Flash-MoE iOS — Run massive MoE models on iPhone

47

anemll-flash-mlx. Python

34

anemll-profile. ANE (Apple Neural Engine) CostModel profiler for CoreML models

33

anemllclaw. TypeScript

27

ds4-ssd. DeepSeek V4 Flash specific inference engine. SSD MoE expert paging (slot-bank) + disk KV cache for long agent sessions. Metal-first, narrow & high-performance.

25

anemll_macOS_agent. Remote control agent for macOS development

13

anemll-thunderbolt-BFP. C++

5

qwen3_apple_style_2bit_qat_lora. WIP: Experiments with 2-bit QAT and LoRA

4

tinygrad. You like pytorch? You like micrograd? You love tinygrad! ❤️

3

homebrew-tap. Homebrew tap for anemll tools

2

coremltools. Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

1

mlx-trm. MLX Implementation of Recursive Reasoning with Tiny Networks

1

anemll-sms-bridge. Python

1

anemll.github.io. Anemll web page

1

netron. Visualizer for neural network, deep learning and machine learning models

1

MPP-4.1-FP4-FP8-block. Metal 4.1 / MPP 4.1 FP4-FP8 block-scaling (MXFP4) probe and benchmarks on Apple M5

1