diff --git a/docs/source/markdown/ramalama-rm.1.md b/docs/source/markdown/ramalama-rm.1.md
new file mode 100644
index 00000000..c26c3406
--- /dev/null
+++ b/docs/source/markdown/ramalama-rm.1.md
@@ -0,0 +1,16 @@
+% ramalama-rm 1
+
+## NAME
+ramalama - Remove specified AI Model from system.
+
+## SYNOPSIS
+**ramalama rm** [*options*] *model*
+
+## DESCRIPTION
+Remove specified AI Model from system
+
+## SEE ALSO
+**[ramalama(1)](ramalama.1.md)
+
+## HISTORY
+Aug 2024, Originally compiled by Dan Walsh <dwalsh@redhat.com>
diff --git a/docs/source/markdown/ramalama.1.md b/docs/source/markdown/ramalama.1.md
index b72c6294..12a38ddb 100644
--- a/docs/source/markdown/ramalama.1.md
+++ b/docs/source/markdown/ramalama.1.md
@@ -19,6 +19,7 @@ Ramalama : The goal of ramalama is to make AI even more boring.
 | [ramalama-pull(1)](ramalama-pull.1.md)  | Pull AI Model from registry to local storage                |
 | [ramalama-push(1)](ramalama-push.1.md)  | Push specified AI Model (OCI-only at present)               |
 | [ramalama-run(1)](ramalama-run.1.md)    | Run a chatbot on AI Model.                                  |
+| [ramalama-rm(1)](ramalama-rm.1.md)      | Remove an AI Model.                                         |
 | [ramalama-serve(1)](ramalama-serve.1.md)| Serve local AI Model as an API Service.                     |
 
 ## CONFIGURATION FILES
diff --git a/ramalama/cli.py b/ramalama/cli.py
index 0ebcaa0d..3c692ecd 100644
--- a/ramalama/cli.py
+++ b/ramalama/cli.py
@@ -23,6 +23,7 @@ def usage():
     print("  list              List models")
     print("  pull MODEL        Pull a model")
     print("  push MODEL TARGET Push a model to target")
+    print("  rm MODEL          Remove a model")
     print("  run MODEL         Run a model")
     print("  serve MODEL       Serve a model")
     sys.exit(1)
@@ -216,6 +217,15 @@ def push_cli(store, args, port):
             f"Unsupported repository type for model: {model}")
 
 
+def rm_cli(store, args, port):
+    if len(args) < 1:
+        usage()
+
+    model = args.pop(0).replace("://", "/")
+    model = f"{store}/models/{model}"
+    exec_cmd(["rm", model])
+
+
 def run_cli(store, args, port):
     if len(args) < 1:
         usage()
@@ -259,4 +269,5 @@ def in_container():
 funcDict["pull"] = pull_cli
 funcDict["push"] = push_cli
 funcDict["run"] = run_cli
+funcDict["rm"] = rm_cli
 funcDict["serve"] = serve_cli
diff --git a/test/ci.sh b/test/ci.sh
index 12d96e20..92499560 100755
--- a/test/ci.sh
+++ b/test/ci.sh
@@ -56,6 +56,12 @@ main() {
   ./${binfile} list | grep tiny-vicuna-1b
   ./${binfile} list | grep NAME
   ./${binfile} list | grep oci://quay.io/mmortari/gguf-py-example/v1/example.gguf
+  ./${binfile} rm ollama://ben1t0/tiny-llm:latest
+  if ./${binfile} list | grep ben1t0/tiny-llm; then
+      exit 1
+  else
+      exit 0
+  fi
 #  ramalama list | grep granite-code
 #  ramalama rm granite-code
 }