From 3a070413e4a57f54da4bd5bca80d77581bb43156 Mon Sep 17 00:00:00 2001
From: Harald Hoyer <harald@hoyer.xyz>
Date: Thu, 21 May 2026 23:11:00 +0200
Subject: [PATCH] chore(halo): upgrade coder model to Q8 quant and bump spec
 draft

Switch the coder model from Q6_K to the UD-Q8_K_XL quant for better
output quality, and raise spec-draft-n-max from 4 to 5 to allow longer
speculative draft sequences.
---
 systems/x86_64-linux/halo/models.ini | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/systems/x86_64-linux/halo/models.ini b/systems/x86_64-linux/halo/models.ini
index f6121b9..5b1bbac 100644
--- a/systems/x86_64-linux/halo/models.ini
+++ b/systems/x86_64-linux/halo/models.ini
@@ -15,9 +15,9 @@ fit                 = on
 c                   = 131072
 
 [coder]
-hf                  = unsloth/Qwen3.6-27B-MTP-GGUF:Q6_K
+hf                  = unsloth/Qwen3.6-27B-MTP-GGUF:UD-Q8_K_XL
 spec-type           = ngram-simple,draft-mtp
-spec-draft-n-max    = 4
+spec-draft-n-max    = 5
 threads-batch       = 16
 temp                = 0.6
 top-p               = 0.95