mission-control-v2/deploy/llama-swap.config.yaml

# Auto-generiert von provision.sh - per Mission Control erweiterbar
healthCheckTimeout: 300
globalTTL: 0

models:
  Qwen3.6-35B-A3B:
    # parallel 2 + c 131072: 2 Slots à 65k (Slot 2 = Mem0-Lern-Extraktion, blockiert Voice-Turns
    # nicht mehr); KV Q8_0 macht das speicherneutral zu vorher (65k f16). Bench 2026-07-02:
    # Q8_0 kostet 0 t/s, MTP n-max 3 = +26% vs. ohne Spec.
    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 131072 -ngl 999 -fa on --no-mmap --jinja --parallel 2 -cram 16384 -ctk q8_0 -ctv q8_0 --spec-type draft-mtp --spec-draft-n-max 3
    ttl: 0
    aliases:
    - hermes
    - fast
    # context = nutzbarer Kontext PRO REQUEST (c geteilt durch parallel-Slots).
    capabilities:
      in: [text]
      out: [text]
      tools: true
      context: 65536
  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
    capabilities:
      in: [text]
      out: [text]
      tools: true
      context: 32768
  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
    capabilities:
      in: [text]
      out: [text]
      tools: true
      context: 131072
  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
    capabilities:
      in: [text, image]
      out: [text]
      context: 32768
  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
    capabilities:
      in: [text]
      out: [text]
      tools: true
      context: 131072
  gpt-oss-120b:
    # heavy-Kandidat (Bench 02.07.: tg 54-55 t/s vs. Qwen3.5-122B 23,5 t/s = 2,3x, 60 statt
    # 73 GB). Noch OHNE heavy-Alias — erst Qualitaets-Check (deutsch/Reasoning), dann Entscheid.
    cmd: |
      llama-server -m /srv/models/gpt-oss-120b-GGUF/gpt-oss-120b-mxfp4-00001-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
    capabilities:
      in: [text]
      out: [text]
      tools: true
      context: 32768
  Qwen3-VL-30B-A3B-Instruct:
    # vision-Upgrade-Kandidat (Bench 02.07.: tg 90-92 t/s, MoE 3B aktiv, stark auf GUI-Benchmarks).
    # Noch OHNE vision-Alias — erst Screenshot-Qualitaets-Check, dann Entscheid (brains-Budget!).
    cmd: |
      llama-server -m /srv/models/Qwen3-VL-30B-A3B-Instruct-GGUF/Qwen3-VL-30B-A3B-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-30B-A3B-Instruct-GGUF/mmproj-F16.gguf --jinja
    ttl: 300
    capabilities:
      in: [text, image]
      out: [text]
      context: 32768
  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
    capabilities:
      in: [text, image]
      out: [text]
      tools: true
      context: 131072
groups:
  brains:
    swap: false
    persist: true
    members:
    - Qwen3-Embedding-0.6B
    - Qwen3-VL-8B-Instruct
    - Qwen3.6-35B-A3B