Skip to content

Head-to-head · Mistral

Magistral Small vs Mixtral 8x7B

Magistral Small needs ~16 GB at Q4_K_M; Mixtral 8x7B needs ~28.9 GB. That ~12.9 GB gap decides which hardware runs each; they differ on 1 of the 14 devices below.

Spec Magistral Small Mixtral 8x7B
Parameters24B46.7B MoE
Memory at Q4_K_M~16 GB~28.9 GB
Context window40k32k
LMArenanot rankednot ranked
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 Mixtral 8x7B
Q2_K 10.1 GB* 19.6 GB*
Q3_K_M 11.7 GB* 22.8 GB*
Q4_K_M 14 GB 26.49 GB
Q5_K_M 17.1 GB* 33.3 GB*
Q6_K 19.7 GB* 38.3 GB*
Q8_0 25 GB 46.22 GB
FP16 47 GB 93.4 GB*

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

Bottom line

The larger Mixtral 8x7B needs ~28.9 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 Mixtral 8x7B.

More Mistral comparisons

FAQ

What is the difference in memory between Magistral Small and Mixtral 8x7B?

At Q4_K_M, Magistral Small needs about 16 GB and Mixtral 8x7B needs about 28.9 GB, a difference of ~12.9 GB.

Should I run Magistral Small or Mixtral 8x7B?

Run Mixtral 8x7B if your hardware has the ~28.9 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 · Mixtral 8x7B · all models × devices.

Sources

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