diff --git a/compilers/ggml.yaml b/compilers/ggml.yaml
new file mode 100644
index 0000000..641c80c
--- /dev/null
+++ b/compilers/ggml.yaml
@@ -0,0 +1,21 @@
+ggml:
+  name: "GGMl"
+
+  image_url: none
+
+  tags:
+    - inference
+    - edge
+    - quantization
+    - apple-silicon
+    - tensor-library
+
+  url: https://ggml.ai
+
+  description: "GGML: GGML is a minimal, C-based tensor library focussed on providing efficient training and inference for popular models on commodity hardware, specifically Apple silicon. It has a number of features that make it ideal for edge deployment such as integer quantization ranging from 8-bit quantization all the way to 4-bit, no third-party dependencies, zero memory allocations at runtime, and support for WebAssembly and WASM SIMD for running in the browser. "
+
+  features:
+    - "Optimized for Apple Silicon"
+    - "Robust quantization support"
+    - "No third-party dependencies"
+    - "Efficient on-device inference"
\ No newline at end of file
diff --git a/tags.yaml b/tags.yaml
index 0cb8cdf..6cdcdb7 100644
--- a/tags.yaml
+++ b/tags.yaml
@@ -2,36 +2,35 @@
 # When possible, a tag that is already listed should be used.
 # Tags must be sorted in alphabetical order.
 tags:
+  - amd
+  - apple-silicon
+  - compilers
   - container
+  - cupy
+  - distillation
+  - edge
+  - frameworks
+  - high-throughput
+  - inference
   - infrastructure
+  - intel
+  - jax
+  - keras
+  - llms
+  - microsoft
   - model-binary
   - model-endpoint
+  - mxnet
+  - nvidia
+  - numpy
+  - onnx
+  - open-source
   - orchestration
   - pruning
-  - tensorization
-  - quantization
   - pytorch
-  - tensorflow
-  - onnx
-  - open-source
-  - intel
-  - sony
-  - distillation
-  - mxnet
-  - microsoft
-  - keras
-  - numpy
-  - jax
-  - cupy
-  - inference
-  - compilers
-  - frameworks
-  - llms
-  - high-throughput
+  - quantization
   - serving
-  - edge
+  - sony
   - tensor-library
-  - apple-silicon
-  - nvidia
-  - amd
-  
+  - tensorization
+  - tensorflow