Update README.md

README.md

@@ -7,11 +7,11 @@ tags:
 
 13 TPS  
 
-27 TPS with Speculative decoding in LMstudio. 
+27 TPS with Speculative decoding in LMstudio, yeah instant 100% upgrade for math/code stuff.
 
 Draft model: [DeepScaleR-1.5B-Preview-Q8](https://huggingface.co/mlx-community/DeepScaleR-1.5B-Preview-Q8)
 
-Macbook M4 Max: high power (10 TPS on low-power, GPU draws only 5 watts)
+Macbook M4 Max: high power (10 TPS on low-power, GPU draws only 5 watts...less than your brain)
 
 system prompt: "You are Fuse01. You answer very direct brief and concise"
 
@@ -57,9 +57,9 @@ if tokenizer.chat_template is not None:
 response = generate(model, tokenizer, prompt=prompt, verbose=True)
 ```
 
-Are you still reading down here?  Really?
+Are you still reading down here?
 
-Maybe use your OCD super powers to try this new Q4 lossless quant compression and tell us how to improve mlx-lm to get 8-bit quality at 4-bit speed! 
-https://huggingface.co/NexaAIDev/DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant
+Maybe check out this new Q4 lossless quant compression from NexaAI and tell the MLX community how to improve mlx-lm to get 8-bit quality at 4-bit speed! 
+[DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant](https://huggingface.co/NexaAIDev/DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant)
 
 ore