OOMPF

budget

structurally valid

The cheapest way to keep working — DeepSeek Flash for the bulk, a local model for chores, Kimi for planning, GLM for review. Reach for it on high-volume, low-stakes work where throughput per dollar matters more than peak quality.

budget#budget#cost-sensitive#deepseek#open-weightby @thekidnamedkd

Providers Providers ↗

DeepSeek ↗Ollama ↗Moonshot AI ↗Z.AI ↗

Source

GitHub source ↗Pinned 70d1123f ↗Indexed source current · checked sha256 a4586e0d…dba1

The indexed metadata matched the source at the last check.

Install Profile layout ↗
oompf add https://oompf.run/p/prof_d2c4ffc29a30f50f68cedfd1bb1139c8

Installs as a native OMP profile. Nothing is overwritten — a name collision fails instead. How installing works

Models Models ↗

Friendly name first; exact selector beneath. Model resolution

Behavior Settings ↗

Model roles Model roles ↗

  • defaultDeepSeek-V4 Flash
  • taskDeepSeek-V4 Flash
  • smolQwen 3.6
  • commitQwen 3.6
  • planKimi K2.6
  • reviewerGLM 5.2

Advisor Advisor ↗

Advisor
disabled

Settings Settings ↗

Symbol preset
default
Default thinking level
low