Comment by silentbob7

Here's my model.ini for 4090 (using the chat template from froggeric):

version = 1

[*] ; Global defaults shared across all presets

threads = 16

[Qwen3.8-27B]

; Model files

model = ..\Qwen3.8-27B-FP8\Qwen3.8-27B-UD-Q4_K_XL.gguf

mmproj = ..\Qwen3.8-27B-FP8\mmproj-BF16.gguf

; Context & compute

ctx-size = 114688

parallel = 1

n-gpu-layers = -1

batch-size = 1024

ubatch-size = 512

flash-attn = on

cache-type-k = q8_0

cache-type-v = q8_0

; Speculative decoding (MTP draft)

spec-default = true

spec-type = draft-mtp

spec-draft-n-max = 5

cache-type-k-draft = q4_0

cache-type-v-draft = q4_0

; Multimodal

no-mmproj-offload = true

; Context behavior

no-context-shift = true

; Chat template & reasoning

jinja = true

reasoning = on

chat-template-kwargs = {"preserve_thinking":"true","reasoning_effort":"medium"}

; Sampling

temp = 1.0

top-n-sigma = 1

top-k = 0

top-p = 1.0

presence-penalty = 0.0

repeat-penalty = 1.0

fit = off

; Auto-load this model when the server starts

load-on-startup = true