0
MODEL SIGNAL · MISTRAL

Mistral Small 4

Efficient small model with configurable reasoning — set reasoning_effort from none to high on the fly. 5x more params than Small 3 but only 6B active per token, 40% faster end-to-end.

CATEGORYGeneral
CONTEXT128K
RELEASEDMarch 15, 2026
Key Features
  • Configurable reasoning effort
  • 6B active params per token
  • 40% faster than Small 3
  • 3x more RPS
  • Apache 2.0

Provider announcement →

Read the Model Signal report →

The Model Signal report for Mistral Small 4 is still compounding. It synthesizes automatically from Signal + Noise wire coverage and the provider announcement — check back as the wire mentions this model.