Back to Mistral Small 4 in the gallery

Mistral AI

Multimodal Mistral Small refresh that jumps from the older dense 24B stack to an MLA-based sparse MoE design.

Mistral Small 4 architecture diagram
Mistral Small 4 architecture diagram. Select the diagram to view it at full size.

Architecture and specifications

Scale
119B total, 6.63B active (5.6% active)
Context (tokens)
262,144
License
Apache License 2.0
Date
2026-03-16
Decoder type
Sparse MoE
Attention
MLA
Layer mix
36 MLA
KV cache / token (bf16) info
22.5 KiB · Very low
Key detail
Uses 128 experts with 4 routed plus 1 shared expert active per token while unifying instruct, reasoning, and vision.

Training and benchmarks

Pretraining data
Not disclosed The model card does not report the pretraining-token total. Mistral Small 4 model card
Post-training methods
Not disclosed The model card describes hybrid reasoning and instruction following but does not identify the post-training methods. Mistral Small 4 model card
AA Intelligence Index v5.0 info
Total score 4.3 Knowledge Work 0.2 Coding 0.0 Science 0.0 General 17.0
AA Intelligence Index v4.3.2 info
Total score 11.3 General 21.1 Scientific 5.1 Coding 19.4 Agents 0.2

Further reading and tools