michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Define four-profile production matrix with Medium default

Browse Source
This commit is contained in:
Mikei386
2026-08-22 11:30:38 +02:00
parent 977f8f5c76
commit 41b9c17f0f
33 changed files with 237 additions and 160 deletions
Download Patch File Download Diff File Expand all files Collapse all files
platform/profiles/profile-medium.conf
+2 -2
View File
@@ -1,6 +1,6 @@
[Unit]
Description=Local AI llama.cpp - Qwen Medium 92K IQ4_XS Pure with CPU Vision
Description=Local AI llama.cpp - Qwen Medium 160K IQ4_XS Pure with CPU Vision
[Service]
ExecStart=
ExecStart=/opt/mike-ai/llama.cpp/build/bin/llama-server --model /opt/mike-ai/models/qwen3.8-27b-iq4-xs-pure/qwen3.8-27b-IQ4_XS-pure.gguf --mmproj /opt/mike-ai/models/qwen3.8-27b-nvfp4/mmproj-BF16.gguf --no-mmproj-offload --alias qwen38-27b-iq4xs-pure-92k --ctx-size 94208 --flash-attn on --cache-type-k q4_0 --cache-type-v q4_0 --threads 6 --threads-batch 6 --batch-size 64 --ubatch-size 32 --parallel 1 --jinja --reasoning auto --host 127.0.0.1 --port 8080 --metrics --fit off --n-gpu-layers all --no-mmap --temperature 0.2 --top-p 0.8 --top-k 20 --device CUDA0 --split-mode none
ExecStart=/opt/mike-ai/llama.cpp/build/bin/llama-server --model /opt/mike-ai/models/qwen3.8-27b-iq4-xs-pure/qwen3.8-27b-IQ4_XS-pure.gguf --mmproj /opt/mike-ai/models/qwen3.8-27b-nvfp4/mmproj-BF16.gguf --no-mmproj-offload --alias qwen-medium --ctx-size 160000 --flash-attn on --cache-type-k q4_0 --cache-type-v q4_0 --threads 6 --threads-batch 6 --batch-size 64 --ubatch-size 32 --parallel 1 --jinja --reasoning auto --host 127.0.0.1 --port 8080 --metrics --fit off --n-gpu-layers all --no-mmap --temperature 0.2 --top-p 0.8 --top-k 20 --device CUDA0,CUDA1 --main-gpu 0 --split-mode layer --tensor-split 90,10 --spec-type draft-mtp --spec-draft-n-max 3 --spec-draft-type-k f16 --spec-draft-type-v f16