Update README.md

README.md

@@ -56,6 +56,7 @@ llama-server --hf-repo hellork/calme-2.1-qwen2-7b-IQ4_NL-GGUF --hf-file calme-2.
 Interact with this model by speaking to it. Lean, fast, & private, networked speech to text, AI images, multi-modal voice chat, control apps, webcam, and sound with less than 4GiB of VRAM.
 [whisper_dictation](https://github.com/themanyone/whisper_dictation)
 
+*Quick start*
 ```bash
 git clone -b main --single-branch https://github.com/themanyone/whisper_dictation.git
 pip install -r whisper_dictation/requirements.txt
@@ -64,10 +65,15 @@ git clone https://github.com/ggerganov/whisper.cpp
 cd whisper.cpp
 GGML_CUDA=1 make -j # assuming CUDA is available. see docs
 ln -s server ~/.local/bin/whisper_cpp_server # (just put it somewhere in $PATH)
-
 whisper_cpp_server -l en -m models/ggml-tiny.en.bin --port 7777
+
+# -ngl option assumes CUDA is available. see docs
+llama-server --hf-repo hellork/calme-2.1-qwen2-7b-IQ4_NL-GGUF --hf-file calme-2.1-qwen2-7b-iq4_nl-imat.gguf -c 2048 -ngl 17 --port 8888
+
+cd whisper_dictation
 ./whisper_cpp_client.py
 ```
+
 See [the docs](https://github.com/themanyone/whisper_dictation) for tips on enabling the computer to talk back, draw AI images, carry out voice commands, and other features.
 
 Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.