Sunk Cost sunkcost.ai Data checked 2026-09-03

What hardware do you need to run Mistral Small 3.2 24B Instruct?

Mistral Small 3.2 24B Instruct at Q4_K_M is 14 GB of weights, with a context ceiling of 128k tokens. Well-rounded, follows instructions tightly, decent function calling. Nothing exceptional.

Cheapest machine that runs itStrix Halo Framework Desktop, 32GB at $1,269
Shortest pay-backMac mini M6, 32GB — Pays back in 134 years
Fastest of the ones listedMac Studio M5 Ultra, 96GB — 46 tok/s at 32k context
Honest answer on costPays back in 163 years at 500k tokens a day.

How good is it, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 7, which puts it in the Below every hosted tier band. Fine for simple, well-specified tasks. Noticeably less capable than anything the big labs sell today. Score source. See the whole table.

What it costs either way

Renting the same model costs $0.075 per million input tokens and $0.2 per million output (OpenRouter, cheapest active endpoint, checked 2026-09-03). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill.

Machines that run it

MachinePriceSpeed at 32kPay-back
Strix Halo Framework Desktop, 32GB $1,269 9.7 tok/s estimated Pays back in 163 years Run the numbers
Mac mini M6, 32GB $1,299 6.5 tok/s estimated Pays back in 134 years Run the numbers
MacBook Pro M5 (14-inch), 32GB $2,399 5.8 tok/s estimated Pays back in 263 years Run the numbers
Mac Studio M5 Max, 36GB $2,499 18 tok/s estimated Pays back in 234 years Run the numbers
DGX Spark GB10 Grace Blackwell, 128GB $4,699 10 tok/s estimated Pays back in 640 years Run the numbers

One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration.

The specifics

Parameters
24B
Quantisation
Q4_K_M
Weights on disk
14 GB
KV cache
5.4 GB at 32k context
Maximum context
128k tokens (128k)
Licence
Apache 2.0
Sources
source 1, source 2