Under Experiment

GOALS: SOTA math reasoning for sub-400M parameter LLM

Benchmark

Note: we use thinking token forcing because this model occasionally output response directly without thinking tag.

Standard Decoding:

Recursive Self-Aggregation:

  • AIME 2025: TBA
  • HMMT 2025: TBA
  • BRUMO 2025: TBA
  • CMIMC 2025: TBA
Downloads last month
20
GGUF
Model size
0.4B params
Architecture
lfm2
Hardware compatibility
Log In to view the estimation

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support