Update README.md

README.md

@@ -15,7 +15,7 @@ system prompt: "You are Fuse01. You answer very direct brief and concise"
 
 prompt: "Write a quick sort in C++"
 
-Temp: 0
+Context: 131072, Temp: 0
 
 
 Try this model & quant in roo coder, starting in Architect Mode and letting it auto switch to Code Mode.... it actually spits decent code for small projects with multiple files.
@@ -25,11 +25,13 @@ All the smaller quants I tested shit the bed
 
 All the smaller models I tested shit the bed
 
-So far (Feb 20, 2025) this is the only model & quant that fits on a Macbook, spits decent code AND works with Speculative Decoding.
+So far (Feb 20, 2025) this is the only model & quant that runs fast on Mac, spits decent code AND works with Speculative Decoding.
 
 
 Huge thanks to all who helped Macs get this far!
 
+Oh, here is the draft model  [DeepScaleR-1.5B-Preview-Q8](https://huggingface.co/mlx-community/DeepScaleR-1.5B-Preview-Q8)
+
 # bobig/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8
 
 The Model [bobig/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8](https://huggingface.co/bobig/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8) was