Skip to content

Mistral AI

Mistral Small 4 (26.03)

119 B params (6.5 B active) · 256k context · Open weights

Released 2026-03-16

Details

Provider
Mistral AI
Family
Mistral Small
Context length
256k tokenssource
Open weights
Yessource
Licence
Apache 2.0source
Parameters (total)
119 Bsource
Active parameters (per token)
6.5 Bsource

API pricing

Input$0.15 per million tokenssource

Output$0.6 per million tokenssource

Checked on 2026-11-12

Running it locally

Memory needed for 119 B parameters (mixture of experts: 6.5 B active per token, but all 119 B must be held in memory) at 8,192 tokens of context. Architecture not recorded, so a flat 1.0 GB KV allowance is used. Estimates, not measurements.

FormatWeightsKV cacheOverheadTotal
Q4 K_M72.7 GB1.0 GB4.1 GB77.9 GB
Q6 K97.6 GB1.0 GB5.4 GB104.0 GB
Q8 0126.4 GB1.0 GB6.8 GB134.3 GB
FP16238.0 GB1.0 GB12.4 GB251.4 GB

Catalogued hardware that fits at Q4

Mini PCs reserve 8.0 GB for the operating system. “Comfortable” keeps at least 10% memory spare.

Benchmarks

No benchmarks for this model yet

We only publish results we can evidence, so there is nothing here yet and we have not filled the gap with estimates. Here is how we will test and label results.