27 lines
610 B
YAML
27 lines
610 B
YAML
manager:
|
|
memory_budget: 450
|
|
contention_policy:
|
|
strategy: wait_then_preempt
|
|
wait_timeout_s: 45
|
|
preempt_after_s: 15
|
|
|
|
models:
|
|
- name: Qwen-Coder-Next
|
|
model: mlx-community/Qwen3-Coder-Next-4bit
|
|
estimated_memory_gb: 50
|
|
reasoning_parser: qwen3
|
|
|
|
- name: Qwen3.6
|
|
model: mlx-community/Qwen3.6-35B-A3B-6bit
|
|
estimated_memory_gb: 40
|
|
reasoning_parser: qwen3
|
|
|
|
- name: gemma
|
|
model: mlx-community/gemma-4-31b-it-8bit
|
|
estimated_memory_gb: 40
|
|
reasoning_parser: gemma4
|
|
|
|
- name: MiniMax-M3
|
|
model: pipenetwork/MiniMax-M3-MLX-mixed-3_6bit
|
|
estimated_memory_gb: 200
|