From 6d5586c63c08db5ce090334d49163f5a3a123d58 Mon Sep 17 00:00:00 2001 From: "K. Isom" Date: Tue, 22 Sep 2026 14:29:01 -0700 Subject: [PATCH] dixie: retire the 4B dialectic model; 9B gets 4 slots over a 48k pool Dialectic benchmark (8 hermes-fleet questions): Qwen3-4B answered in 2-12 s but often wrongly (invented facts, 'no information' on things memory holds); the 9B answered correctly. All Honcho dialectic levels now use the 9B (rift .env). Its VRAM goes to the 9B's KV pool: at 2 x 16k, concurrent deriver + dialectic hit 'failed to find free space in the KV cache'. 9B 6.3 GB + embed 2.2 GB = 8.4 GB. Co-Authored-By: Claude Opus 5.5 (1M context) --- hw/dixie/default.nix | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/hw/dixie/default.nix b/hw/dixie/default.nix index ebb45e4..ac3f0e4 100644 --- a/hw/dixie/default.nix +++ b/hw/dixie/default.nix @@ -40,6 +40,11 @@ let ; web_extract) for all agents and Honcho's deriver/summary/dream model. [ornith-1.5-9b-uncensored] model = ${modelsDir}/ornith-1.5-9b-uncensored/Ornith-1.5-9B-uncensored.Q4_K_M.gguf + ; serves the deriver, all dialectic levels and three agents' approval guardians at once: + ; 4 slots over one 48k pool (at 2 x 16k, concurrent deriver + dialectic hit "failed to find + ; free space in the KV cache" and stalled) + ctx-size = 49152 + parallel = 4 ; Runaway guard carried over from straylight: helper tasks need short answers. reasoning-budget = 2048 n-predict = 4096 @@ -52,10 +57,9 @@ let top-k = 20 min-p = 0 - ; Honcho dialectic: non-thinking instruct model so answers are short and fast. - [honcho-dialectic] - model = ${modelsDir}/qwen3-4b-instruct-2507/Qwen3-4B-Instruct-2507-Q4_K_M.gguf - n-predict = 1024 + ; honcho-dialectic (Qwen3-4B-Instruct-2507) retired 2026-09-22: fast but often wrong in a + ; dialectic benchmark, where the 9B answered correctly. All dialectic levels use the 9B now; + ; the 4B's VRAM went to the 9B's KV pool. File stays on the stick under qwen3-4b-instruct-2507/. ; Honcho embeddings (1024-dim; EMBEDDING_VECTOR_DIMENSIONS=1024 on rift). [honcho-embed] @@ -175,8 +179,8 @@ in }; systemd.services.llama-server = llamaService { - description = "llama.cpp router: helper tier (9B guardian/deriver, dialectic, embeddings)"; - port = 11434; preset = llamaModelsIni; modelsMax = 3; + description = "llama.cpp router: helper tier (9B guardian/deriver/dialectic, embeddings)"; + port = 11434; preset = llamaModelsIni; modelsMax = 2; }; systemd.services.llama-vision = llamaService { description = "llama.cpp vision server (qwen3-vl-8b, on demand)";