Update 2026-04-22-ai-agency.md

Author: shannona

_posts/2026-04-22-ai-agency.md

@@ -74,18 +74,42 @@ Local AI on your own silicon is Self-Sovereign Computing in practice.  Apple Sil
 It's also really coming of its own. Some recent advancements in leveraging the M-series silicon have double the inference speed of certain models:
 
 **Metal (Q4_K_M quantization):**
-| |M1 Max (64GB)  |  M5 Max (128GB) |
-|----|-------|-----------|
-| Prompt eval: |       64 tok/s          |        180 tok/s |
-| Decode: |                 27 tok/s   |                 58 tok/s |
-
+<table>
+  <tr>
+    <td></td>
+    <td>M1 Max (64GB)</td>
+    <td>M5 Max (128GB)</td>
+  </tr>
+  <tr>
+    <td>Prompt eval:</td>
+    <td>64 tok/s</td>
+    <td>180 tok/s</td>
+  </tr>
+  <tr>
+    <td>Decode:</td>
+    <td>27 tok/s</td>
+    <td>58 tok/s</td>
+  </tr>
+</table>
 
 **MLX (nvfp4 quantization):**
-| |M1 Max (64GB)  |  M5 Max (128GB) |
-|----|-------|-----------|
-| Prompt eval: |        9 tok/s     |               14 tok/s |
-| Decode:        |       52 tok/s         |         111 tok/s |
-
+<table>
+  <tr>
+    <td></td>
+    <td>M1 Max (64GB)</td>
+    <td>M5 Max (128GB)</td>
+  </tr>
+  <tr>
+    <td>Prompt eval:</td>
+    <td>9 tok/s</td>
+    <td>14 tok/s</td>
+  </tr>
+  <tr>
+    <td>Decode:</td>
+    <td>52 tok/s </td>
+    <td>111 tok/s</td>
+  </tr>
+</table>
 
 We built Self-Sovereign Identity so that your keys and credentials could stay under your control rather than being held by a platform that could revoke them. Local inference is the same principle applied to AI: the model runs where you do, on hardware you own. Combined with a self-sovereign wallet holding your keys and credentials, this is a complete stack where nothing about your digital life requires asking permission from a third party.