What hardware do you need to run Devstral 2 123B?

Devstral 2 123B at Q4_K_M is 75 GB of weights, with a context ceiling of 256k tokens. Dense 123B: every parameter is read for every token, so it is slow as well as large. On the cheapest machine that runs it, a Framework Desktop, 128GB, it generates 2.2 tok/s at 32k of context, worked out from memory bandwidth.

How good is Devstral 2 123B, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 9, 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 Gemma 4 E4B above it, vs DeepSeek-R1-Distill-Qwen-32B below. One more model needs much the same memory at 32k of context: vs GLM-4.5-Air.

What Devstral 2 123B costs either way

Renting the same model costs $0.4 per million input tokens and $2 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 2 123B

Every machine here runs it, but not to the same length. The Strix Halo Framework Desktop, 128GB stops at 32k; the DGX Spark GB10 Grace Blackwell, 128GB takes it to 64k. 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: 17 of the 56 machines on this site hold it at 32k. Within a family only memory decides, so that is every NVIDIA card with 96GB or more, every Mac Studio, Strix Halo box and MacBook Pro with 128GB or more 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 256k 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 17 tok/s.

The cheapest machine that runs it is sold with 128 GB. There is a page on what 128 GB runs, machine by machine: it names the 11 machines here sold at that size, and the 39 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 96 GB, on the RTX PRO 6000 Blackwell, 96GB at $18,000, card only, which hands a model 95 GB.

Run Devstral 2 123B at 64k on the DGX Spark GB10 Grace Blackwell, 128GB

How much memory does Devstral 2 123B need at 256k?

Every figure above is priced at 32k of context. At 256k, which is this model's own ceiling and the longest the calculator offers, Devstral 2 123B needs 169.4 GB rather than 86.7 GB. The weights are the same either way; the key-value cache goes from 11.8 GB to 94.5 GB.

12 of the 37 machines here still sold at a published price hold Devstral 2 123B at 32k and one holds it at 256k. The cheapest still sold goes from the Framework Desktop, 128GB at $3,449 to the Mac Studio M5 Ultra, 256GB at $10,799.

On the Mac Studio M5 Ultra, 256GB it runs 10 tok/s estimated at 32k and 5.3 tok/s estimated at 256k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

The specifics

Parameters

125B

Quantisation

Q4_K_M

Weights on disk

75 GB

KV cache

12 GB at 32k context — Dense, all 88 layers full attention — the context cost is the highest on this list per token. How weights and cache add up.

Maximum context

256k tokens

Licence

other (see repo)

Sources

mistralai/Devstral-2-123B-Instruct-2512