diff --git a/manual/tracy.tex b/manual/tracy.tex index c8c41b94..9c61f964 100644 --- a/manual/tracy.tex +++ b/manual/tracy.tex @@ -5039,13 +5039,16 @@ version = 1 cache-type-k = q8_0 cache-type-v = q8_0 -[unsloth/Qwen3.6-27B-MTP-GGUF:Q4_K_M] +[unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q4_K_M] +hf = unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q4_K_M parallel = 1 spec-default = true spec-type = draft-mtp chat-template-kwargs = {"preserve_thinking": true} +ctx-size = 100000 [nomic-ai/nomic-embed-text-v1.5-GGUF:Q4_K_M] +hf = nomic-ai/nomic-embed-text-v1.5-GGUF:Q4_K_M embedding = true parallel = 4 ctx-size = 8192 @@ -5057,7 +5060,7 @@ cache-ram = 0 The models will be automatically downloaded when trying to access them for the first time. It may take some time. -To get faster response speed you may try replacing \texttt{unsloth/Qwen3.6-27B-MTP-GGUF:Q4\_K\_M} with \texttt{unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q4\_K\_M} in the configuration file. +If you have the resources available you may try replacing \texttt{unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q4\_K\_M} with \texttt{unsloth/Qwen3.6-27B-MTP-GGUF:Q4\_K\_M} in the configuration file to get a more capable model. \subsection{Service provider}