From 993199fba1e7997647c545f5493877b4df1f36d0 Mon Sep 17 00:00:00 2001 From: Spencer Gilbert Date: Thu, 3 Sep 2026 22:01:34 -0400 Subject: [PATCH] [llama.cpp] Switch 3.8-flash-next to Q4_K_XL --- llama/models.ini | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama/models.ini b/llama/models.ini index 560e81f..a9fa91d 100644 --- a/llama/models.ini +++ b/llama/models.ini @@ -78,7 +78,7 @@ repeat-penalty = 1.0 ; GGUF has been re-converted with --mtp. ; --------------------------------------------------------------------------- [qwen3.8-flash-next] -model = /home/spencer/.cache/models/Qwen3.8-Flash-Next-UD-Q2_K_XL-00001-of-00004.gguf +model = /home/spencer/.cache/models/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf mmproj = /home/spencer/.cache/models/Qwen3.8-Flash-Next-mmproj-BF16.gguf chat-template-file = /home/spencer/.config/llama.cpp/qwen-fixed-chat_template.jinja reasoning-format = deepseek -- 2.51.2