frank-small: swap the payload to Ornith-1.5-9B Q8_0 + BF16 mmproj

scripts/frank-small.env

@@ -1,5 +1,5 @@
 # frank-small — llama.cpp (master, CUDA sm_86) serving
-# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K on the RTX 3090, :7771.
+# ornith-ai/Ornith-1.5-9B-GGUF:Q8_0 on the RTX 3090, :7771.
 #
 # 2026-10-03 (Frank, second move): the rung went Q5_K_M -> Q6_K with the pool
 # HELD at 401,408. The freed third slot funded exact f16 V first; the ~3.5 GiB
@@ -45,14 +45,14 @@
 # and the third slot is gone. The flags stay explicit so the choice is visible
 # in the argv either way.
 LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server
-MODEL_FILE=/home/dank/models/MiMo-Q6K/MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf
+MODEL_FILE=/home/dank/models/Ornith-Q8/Ornith-1.5-9B-Q8_0.gguf
 
 # Vision: the Q6_K GGUF ships no `v.*` tensors either, so the projector file
 # IS the vision capability (sha256 ff348f31..., 918,166,048 B, fetched by
 # scripts/download-frank-small.sh; hardlinked into this dir from MiMo-Q5KM/,
 # same bytes — the Q6_K dir is self-contained). Empty string = text-only on
 # purpose.
-MMPROJ_FILE=/home/dank/models/MiMo-Q6K/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf
+MMPROJ_FILE=/home/dank/models/Ornith-Q8/mmproj-Ornith-1.5-9B-BF16.gguf
 
 # Fleet endpoint: same port and alias as every frank-small before it, so the
 # harness models.yml id and the homepage probe do not move.