version = 1

[unsloth/gpt-oss-20b-GGUF:Q8_0]
jinja = on
temp = 1.0
top-k = 0.0
top-p = 1.0
min-p = 0.0
load-on-startup = on
chat-template-kwargs = {"reasoning_effort": "high"}

[unsloth/gpt-oss-120b-GGUF:UD-Q4_K_XL]
jinja = on
load-on-startup = on
temp = 1.0
top-k = 0.0
top-p = 1.0
min-p = 0.0
chat-template-kwargs = {"reasoning_effort": "high"}

[unsloth/gemma-3n-E4B-it-GGUF:Q8_0]
jinja = on
load-on-startup = on
ctx-size = 32768
temp = 1.0
top-k = 64
top-p = 0.95
min-p = 0.0

[henry1477/Qwen3-Embedding-4B-gguf]
embedding = on
pooling = cls
ubatch-size = 8192

[ggml-org/Ministral-3-14B-Reasoning-2512-GGUF]
temp = 0.7
top-p = 0.95

[ggml-org/Ministral-3-14B-Instruct-2512-GGUF]
temp = 0.1

[ggml-org/Nemotron-Nano-3-30B-A3B-GGUF]
jinja = on
ctx-size = 1048576
fit = on
special = on
load-on-startup = on

[unsloth/MiniMax-M2.1-GGUF:Q3_K_XL]
jinja = on

[unsloth/SmolLM2-1.7B-Instruct-GGUF:Q8_0]
jinja = on