Skip to content

Head-to-head · Mistral

Magistral Small vs Mistral Small 3 24B

Magistral Small needs ~16 GB at Q4_K_M; Mistral Small 3 24B needs ~16.3 GB. That ~0.3 GB gap decides which hardware runs each; they differ on 0 of the 14 devices below.

Spec Magistral Small Mistral Small 3 24B
Parameters24B24B
Memory at Q4_K_M~16 GB~16.3 GB
Context window40k128k
LMArenanot rankedElo 1357
LicenseApache-2.0Apache-2.0

Which devices run each

A representative spread across the memory range. Tap a verdict for the full breakdown.

Size at each quantization

Quant Magistral Small Mistral Small 3 24B
Q2_K 10.1 GB* 10.1 GB*
Q3_K_M 11.7 GB* 11.7 GB*
Q4_K_M 14 GB 14.33 GB
Q5_K_M 17.1 GB* 17.1 GB*
Q6_K 19.7 GB* 19.7 GB*
Q8_0 25 GB 25.05 GB
FP16 47 GB 48 GB*

* derived from bits-per-weight; unstarred sizes are measured GGUF files.

Bottom line

The larger Mistral Small 3 24B needs ~16.3 GB; Magistral Small runs on lighter hardware at ~16 GB with more headroom and faster responses. Check each against your exact device: what runs Magistral Small · what runs Mistral Small 3 24B.

More Mistral comparisons

FAQ

What is the difference in memory between Magistral Small and Mistral Small 3 24B?

At Q4_K_M, Magistral Small needs about 16 GB and Mistral Small 3 24B needs about 16.3 GB, a difference of ~0.3 GB.

Should I run Magistral Small or Mistral Small 3 24B?

Run Mistral Small 3 24B if your hardware has the ~16.3 GB it needs and you want maximum quality; run Magistral Small (~16 GB) for lighter hardware, faster responses, and more memory headroom.

Full breakdowns: Magistral Small · Mistral Small 3 24B · all models × devices.

Sources

Memory figures are estimates at Q4_K_M, validated 2026-08-03. See methodology.