blob: cf34761b332fc4f2ff89b1e7f847a0ac6dd80f85 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
|
version = 1
[*]
fit = on
fit-target = 1024
LLAMA_ARG_KV_OFFLOAD = false
[gpt-oss-20b]
model = /mnt/llms/gpt-oss-20b-Q8_0.gguf
ctx-size = 131072
temp = 1.0
top-p = 1.0
top-k = 0
reasoning = high
[qwen3-coder-30b]
model = /mnt/llms/Qwen3-Coder-30B-A3B-Instruct-UD-Q3_K_XL.gguf
ctx-size = 131072
cache-type-k = q8_0
cache-type-v = q8_0
temp = 0.7
top-k = 20
top-p = 0.8
repeat-penalty = 1.05
[qwen3-coder-30b-Q4]
model = /mnt/llms/Qwen3-Coder-30B-A3B-Instruct-UD-Q4_K_XL.gguf
ctx-size = 49152
cache-type-k = q8_0
cache-type-v = q8_0
threads = 8
temp = 0.7
top-k = 20
top-p = 0.8
repeat-penalty = 1.05
|
