From 6ce527741b5faf94e263aef43d3846719481333c Mon Sep 17 00:00:00 2001
From: Haylan <code@arthurerlich.ch>
Date: Fri, 6 Nov 2026 18:49:05 +0100
Subject: [PATCH] chore(env): lower DFlash2 --spec-draft-n-max to 3 for
 long-context acceptance

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 .env.example | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.env.example b/.env.example
index a636c7b..81d5ae6 100644
--- a/.env.example
+++ b/.env.example
@@ -9,7 +9,7 @@ LLAMA_CACHE_RAM=0
 LLAMA_KV_CACHE_TYPE=q8_0
 
 # Blank = speculative decoding off; see docs/architecture.md#llama-server
-LLAMA_SPEC_ARGS=--spec-type draft-dflash -md /models/Qwen3.8-27B-DFlash2-Q8_0.gguf --spec-draft-n-max 7
+LLAMA_SPEC_ARGS=--spec-type draft-dflash -md /models/Qwen3.8-27B-DFlash2-Q8_0.gguf --spec-draft-n-max 3
 
 # --- SearXNG web search --- see docs/gateway.md#web-search
 # Auto-filled by update.sh — leave blank.