fix(halo): context

systems/x86_64-linux/halo/models.ini

@@ -2,7 +2,6 @@ version = 1
 
 [*]
 flash-attn          = on
-parallel            = 2
 jinja               = true
 n-gpu-layers        = 99
 threads             = 8
@@ -16,15 +15,18 @@ min-p               = 0.0
 mmap                = false
 no-context-shift    = true
 chat-template-kwargs = {"preserve_thinking": true}
-c                   = 524288
 fit                 = on
 spec-type           = draft-mtp
 
 [Qwen3.6-35B-A3B]
-hf                  = unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q6_K
+hf                  = unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q8_K_XL
 spec-draft-n-max    = 3
+parallel            = 1
+c                   = 262144
 
 [Qwen3.6-27B]
 hf                  = unsloth/Qwen3.6-27B-MTP-GGUF:Q6_K
 spec-draft-n-max    = 6
+parallel            = 2
+c                   = 524288