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

2026-09-21 18:20:21 +02:00
parent 9fc7854751
commit 2fa113cd15
10 changed files with 32 additions and 43 deletions
@@ -165,6 +165,13 @@ mmproj             = /home/anon/software/models/mmproj-Qwen3.6-35B-A3B-F16.gguf
                                 # 13.9 used / 3.3 free (2.8 dirty baseline), decode unchanged at 36-37 t/s.
 spec-type          = draft-mtp
 spec-draft-n-max   = 2
+reasoning-budget   = 8192        # "MEDIUM" thinking (added 2026-09-21 when this became the default model in
+                                 # opencode/pi/aichat): caps runaway 15-20k-token think loops, leaves 16k of
+                                 # the 24k ctx for prompt+answer; normal traces (0.5-5k) are untouched. The
+                                 # Qwen3.6 template knows only enable_thinking on/off (no reasoning_effort
+                                 # levels — verified in the gguf header), so this budget IS the depth knob.
+                                 # -1 = unlimited (old behaviour), 0 = the MTP alias. b10615's server README
+                                 # documents N>0; if startup rejects it → set -1 and update llama.cpp.
 ctx-size           = 24576       # thinking eats ctx — same footprint as the non-thinking preset
 n-gpu-layers       = 99
 n-cpu-moe          = 16