Update README.md

README.md

@@ -98,8 +98,8 @@ think correctly. A highly degraded quant like `Q2_K` may not make a
 great encyclopedia, but it's still capable of logical reasoning and
 the emergent capabilities LLMs exhibit.
 
-Good quants for reading (evaluation speed) are BF16, F16, Q4\_0, and
-Q8\_0 (ordered from fastest to slowest). Prompt evaluation is bounded by
+Good quants for reading (evaluation speed) are BF16, F16, Q8\_0, and
+Q4\_0 (ordered from fastest to slowest). Prompt evaluation is bounded by
 computation speed (flops) which means performance can be improved by
 software engineering, e.g. BLAS algorithms, in which case quantization
 starts hurting more than it helps, since it competes for CPU resources