b1aebf90dbf374628af8036c197827896db4459d
- Author
- TheEdgeOfRage <git@theedgeofrage.com>
- Committer
- TheEdgeOfRage <git@theedgeofrage.com>
- Date
Message
Remove qwen 3.6 35B A3B model
Diff
1diff --git a/dot_config/llama-server/models.ini b/dot_config/llama-server/models.ini
2index 9326ec81e555b904cfa8e129ad69b1e5afa806cc..df278966f9947b2200197c47ba61b549ad026103 100644
3--- a/dot_config/llama-server/models.ini
4+++ b/dot_config/llama-server/models.ini
5@@ -35,21 +35,6 @@ repeat-penalty = 1.0
6 reasoning = on
7 chat-template-kwargs = {"reasoning_effort":"medium"}
8
9-[unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_S]
10-hf = unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_S
11-alias = qwen3.6-35b-a3b
12-n-gpu-layers = 99
13-flash-attn = on
14-jinja = true
15-ctx-size = 65536
16-temp = 0.9
17-top-p = 0.95
18-top-k = 20
19-min-p = 0.0
20-parallel = 1
21-repeat-penalty = 1.0
22-reasoning = on
23-
24 [unsloth/gemma-4-26B-A4B-it-qat-GGUF:Q4_K_XL]
25 hf = unsloth/gemma-4-26B-A4B-it-qat-GGUF:UD-Q4_K_XL
26 alias = gemma4-26b-a4b