From 9e0c918b6e6bda74459919a60fd5f1b3daca0401 Mon Sep 17 00:00:00 2001 From: Frank Date: Mon, 21 Sep 2026 15:06:05 -0700 Subject: [PATCH] docs(frank-small): record the CACHE_RAM=2048 cap in the deployed flags --- serverAppConfigs-docs/LLM/frank-small-gemma4-12b.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/serverAppConfigs-docs/LLM/frank-small-gemma4-12b.md b/serverAppConfigs-docs/LLM/frank-small-gemma4-12b.md index 1e7c0ff..6e382cb 100644 --- a/serverAppConfigs-docs/LLM/frank-small-gemma4-12b.md +++ b/serverAppConfigs-docs/LLM/frank-small-gemma4-12b.md @@ -133,7 +133,7 @@ prefill ~254k tokens / decode at ~253k context: Repo truth: `scripts/frank-small.env` + `scripts/serve-frank-small.sh`. Key values: `MODEL_DIR=/home/dank/models/Gemma4-12B-QAT`, `MODEL_FILE=Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf`, -`DRAFT_FILE=mtp-gemma-4-12B-it.gguf`, `CACHE_TYPE_K=V=q8_0`, +`DRAFT_FILE=mtp-gemma-4-12B-it.gguf`, `CACHE_TYPE_K=V=q8_0`, `CACHE_RAM=2048`, `SPEC_TYPE=draft-mtp,ngram-mod`, `SPEC_DRAFT_N_MAX=3`, `POLL_LEVEL=50`, `CTX_SIZE=1048576` with `PARALLEL=4` (four full 262,144-token slots), `BATCH_SIZE=8192`, `UBATCH_SIZE=1024`, `NGL=999`, `FLASH_ATTN=on`,