Update README.md

README.md

@@ -96,19 +96,7 @@ CLI (with reasoning/thinking)
     --temp 0.6 \
     --reasoning on \
     --reasoning-budget -1
-CLI (with MTP self-speculative — higher throughput)
-./build/bin/llama-cli \
-    -m ~/Downloads/Hy3-IQ1_M-mtp.gguf \
-    -c 65536 \
-    -ngl 99 -fa on \
-    --spec-type draft-mtp \
-    --spec-draft-n-max 3 \
-    --spec-draft-n-min 1 \
-    -ctk q8_0 -ctv q8_0 \
-    -ctkd q8_0 -ctvd q8_0 \
-    -p "Hello" \
-    -n 200 \
-    --temp 0.6
+
 Server (OpenAI-compatible API)
 ./build/bin/llama-server \
     -m ~/Downloads/Hy3-IQ1_M-mtp.gguf \
@@ -127,20 +115,7 @@ curl http://localhost:8080/v1/chat/completions \
     "temperature": 0.6,
     "max_tokens": 200
   }'
-Server (with reasoning + MTP)
-./build/bin/llama-server \
-    -m ~/Downloads/Hy3-IQ1_M-mtp.gguf \
-    -c 65536 \
-    -ngl 99 -fa on \
-    --spec-type draft-mtp \
-    --spec-draft-n-max 3 \
-    --spec-draft-n-min 1 \
-    -ctk q8_0 -ctv q8_0 \
-    -ctkd q8_0 -ctvd q8_0 \
-    --temp 0.6 \
-    --reasoning on \
-    --reasoning-budget -1 \
-    --port 8080
+
 For Mac with 96 GB RAM
 # No MTP, compressed KV cache
 ./build/bin/llama-cli \