Hitonabi
e08d812598
- Bench-Matrix Qwen3.6 (5 Configs, separater Port): MTP n-max 3 bestaetigt (+26% tg), n-max 4 lohnt nicht, KV Q8_0 gratis (78,6=78,6 t/s) bei halbem KV-Speicher - deploy-Config: -ctk/-ctv q8_0 am hermes-Eintrag (Live-Schaltung: User-Freigabe noetig) - voice.py: chat_first_content-Metrik (echte Hirn-Latenz bis erster Inhalts-Token) - Report um Umsetzungs-Nachtrag ergaenzt Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
57 lines
2.2 KiB
YAML
57 lines
2.2 KiB
YAML
# Auto-generiert von provision.sh - per Mission Control erweiterbar
|
|
healthCheckTimeout: 300
|
|
globalTTL: 0
|
|
|
|
models:
|
|
Qwen3.6-35B-A3B:
|
|
cmd: |
|
|
llama-server -m /srv/models/Qwen3.6-35B-A3B-MTP-GGUF/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 65536 -ngl 999 -fa on --no-mmap --jinja --parallel 1 -cram 16384 -ctk q8_0 -ctv q8_0 --spec-type draft-mtp --spec-draft-n-max 3
|
|
ttl: 0
|
|
aliases:
|
|
- hermes
|
|
- fast
|
|
Qwen3.5-122B-A10B:
|
|
cmd: |
|
|
llama-server -m /srv/models/Qwen3.5-122B-A10B-GGUF/Q4_K_M/Qwen3.5-122B-A10B-Q4_K_M-00001-of-00003.gguf --host 127.0.0.1 --port ${PORT} -c 32768 -ngl 999 -fa on --no-mmap --jinja --cache-reuse 256 -cram 16384
|
|
ttl: 600
|
|
aliases:
|
|
- heavy
|
|
Qwen3-Coder-Next:
|
|
cmd: |
|
|
llama-server -m /srv/models/Qwen3-Coder-Next-GGUF/Qwen3-Coder-Next-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 131072 -ngl 999 -fa on --no-mmap --jinja --cache-reuse 256 -cram 16384
|
|
ttl: 600
|
|
aliases:
|
|
- coder
|
|
Qwen3-VL-8B-Instruct:
|
|
cmd: |
|
|
llama-server -m /srv/models/Qwen3-VL-8B-Instruct-GGUF/Qwen3VL-8B-Instruct-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 32768 -ngl 999 -fa on --no-mmap --mmproj /srv/models/Qwen3-VL-8B-Instruct-GGUF/mmproj-Qwen3VL-8B-Instruct-F16.gguf --jinja
|
|
ttl: 300
|
|
aliases:
|
|
- vision
|
|
Qwen3-Embedding-0.6B:
|
|
cmd: |
|
|
llama-server -m /srv/models/Qwen3-Embedding-0.6B-GGUF/Qwen3-Embedding-0.6B-Q8_0.gguf --host 127.0.0.1 --port ${PORT} --embedding --pooling last -ngl 999 -fa on --no-mmap -c 8192
|
|
ttl: 0
|
|
aliases:
|
|
- embed
|
|
Qwen3-Coder-30B-A3B-Instruct:
|
|
cmd: |
|
|
llama-server -m /srv/models/Qwen3-Coder-30B-A3B-Instruct-GGUF/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 131072 -ngl 999 -fa on --no-mmap --jinja --cache-reuse 256 -cram 16384
|
|
ttl: 300
|
|
aliases:
|
|
- coder-lite
|
|
GLM-4.6V-Flash:
|
|
cmd: |
|
|
llama-server -m /srv/models/GLM-4.6V-Flash-GGUF/GLM-4.6V-Flash-Q4_K_M.gguf --host 127.0.0.1 --port ${PORT} -c 131072 -ngl 999 -fa on --no-mmap --mmproj /srv/models/GLM-4.6V-Flash-GGUF/mmproj-BF16.gguf --jinja
|
|
ttl: 300
|
|
aliases:
|
|
- scout
|
|
groups:
|
|
brains:
|
|
swap: false
|
|
persist: true
|
|
members:
|
|
- Qwen3-Embedding-0.6B
|
|
- Qwen3-VL-8B-Instruct
|
|
- Qwen3.6-35B-A3B
|