What hardware do you need to run Devstral Small 2 24B?

Devstral Small 2 24B at Q4_K_M is 14 GB of weights, with a context ceiling of 384k tokens. Mistral's coding model, with an unusually long context for its size. On the cheapest machine that runs it, a Framework Desktop, 32GB, it generates 9.7 tok/s at 32k of context, worked out from memory bandwidth.

How good is Devstral Small 2 24B, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 8, 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. See the whole table.

Head to head with its neighbours on the leaderboard: vs LFM2.5 2.6B above it, vs Llama 3.1 8B Instruct below. Also head to head: vs Mistral Small 3.2 24B Instruct, the last-generation Mistral nearest it in size. Two more models need much the same memory at 32k of context: vs GLM-4.7-Flash, vs Gemma 3 27B it.

What Devstral Small 2 24B costs either way

Nobody rents Devstral Small 2 24B by the token. The closest hosted match, gpt-oss-20b, costs $0.018 per million input tokens and $0.09 per million output (OpenRouter, cheapest active endpoint, checked 2026-10-29). 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. What a million tokens costs each way puts the two prices side by side.

Machines that run Devstral Small 2 24B

Every machine here runs it, but not to the same length. The Strix Halo Framework Desktop, 32GB stops at 32k; the DGX Spark GB10 Grace Blackwell, 128GB takes it to 256k, the longest the calculator offers. The weights are the same size on every machine; what differs is the memory left for the key-value cache, which grows with every token you keep.

The table is the cheapest machine in each family, not the only one that runs it: 44 of the 56 machines on this site hold it at 32k. Within a family only memory decides, so that is every Mac Studio and Strix Halo box at any size, every NVIDIA card with 24GB or more, every Mac mini and MacBook Pro with 32GB or more, the Radeon AI PRO R9700, 32GB and the DGX Spark, 128GB. One table sets every machine against the others: price, the memory its GPU can use, what it holds and how long it takes to pay for itself.

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 longest context is the longest setting the calculator offers that the machine still holds this model at, cache included, and no machine is shown taking it past its own 384k limit. Each one opens the calculator on that machine at that length.

For scale, the calculator starts from 80 tok/s for a hosted API and times a local machine against it. Nothing above reaches it, and the quickest is 63 tok/s.

The cheapest machine that runs it is sold with 32 GB. There is a page on what 32 GB runs, machine by machine: it names the 6 machines here sold at that size, and the 32 current models the roomiest of them holds at 32k, this one among them.

It fits in less memory than that: the smallest size here that runs it at 32k is 24 GB, on the GeForce RTX 3090, 24GB at $1,499, card only, which hands a model 23 GB and is no longer sold.

Run Devstral Small 2 24B at 256k on the DGX Spark GB10 Grace Blackwell, 128GB

How much memory does Devstral Small 2 24B need at 256k?

Every figure above is priced at 32k of context. At 256k, the longest the calculator offers, Devstral Small 2 24B needs 57.3 GB rather than 19.7 GB. The weights are the same either way; the key-value cache goes from 5.4 GB to 42.9 GB.

30 of the 37 machines here still sold at a published price hold Devstral Small 2 24B at 32k and 13 hold it at 256k. The cheapest still sold goes from the Framework Desktop, 32GB at $1,269 to the Framework Desktop, 128GB at $3,449.

On the Framework Desktop, 128GB it runs 9.7 tok/s estimated at 32k and 3.4 tok/s estimated at 256k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

Two more machines, at a shorter window

The table above lists the machines that run it at 32k, the context the calculator starts on, where Devstral Small 2 24B needs 20 GB. Two more machines hold it at a shorter window, because the weights are the same size either way and the key-value cache is not. The cheapest of those is the Mac mini M6, 24GB at $1,099. The table above starts at $1,269.

One machine per family, cheapest first, from the same list as the table above. Each window is the longest setting the calculator offers that the machine still holds this model at, and it opens the calculator on that machine at that length. What it needs there is the weights plus the key-value cache at that window, measured against the memory each machine's GPU can address, which that machine's own page gives.

The specifics

Parameters

24B

Quantisation

Q4_K_M

Weights on disk

14 GB

KV cache

5.4 GB at 32k context — All 40 layers full attention; no sliding window. How weights and cache add up.

Maximum context

384k tokens

Licence

Apache 2.0

Sources

mistralai/Devstral-Small-2-24B-Instruct-2512