[qwen3.8-27b-a]
model = Huihui-Qwen3.8-27B-abliterated.IQ4_XS.gguf
gpu-layers = 64
ctx-size = 262144
cache-type-k = q4_0
cache-type-v = q4_0
spec-type = draft-mtp
spec-draft-n-max = 2
jinja = true
chat-template-kwargs = {"reasoning_effort": "low"}
mmap = true
flash-attn = true
split-mode = layer