[Sync] LLM clients → Qwen3.6-35B-A3B-Thinking default, Ornith preset, fl GPU monitor abbrs

wm/.config/aichat/config.yaml

@@ -5,7 +5,7 @@
 # see https://github.com/sigoden/aichat/blob/main/config.example.yaml
 keybindings: vi
 editor: nvim
-model: duskadiy:Qwen3-Coder-30B-Instruct-UD-Q3_K_XL
+model: duskadiy:Qwen3.6-35B-A3B-Thinking
 
 # Sessions: persist REPL sessions and keep more history before summarizing.
 # The default compress_threshold (4000) summarizes far too early for 24k+ windows.
@@ -51,6 +51,11 @@ clients:
     supports_vision: true
   - name: GLM-4.7-Flash-UD-Q4_K_XL
     max_input_tokens: 22000            # ctx 24576 · ~21 t/s — quality coder
+  - name: GLM-4.7-Flash-UD-Q3_K_XL
+    max_input_tokens: 22000            # ctx 24576 · ~28 t/s — fast coder (3-bit)
+  - name: Ornith-1.5-35B-A3B-IQ3_XXS
+    max_input_tokens: 22000            # ctx 24576 · ~32 t/s — agentic coder, thinking
+    supports_vision: true
   - name: gpt-oss-20b
     max_input_tokens: 62000            # ctx 65536 · ~38 t/s — fast reasoning + tools
   - name: gpt-oss-20b-low