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. Not yet rated: released after our last ratings pass. Dense 123B: every parameter is read for every token, so it is slow as well as large.
How good is it, 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. Score source. See the whole table.
- Summarising — not rated
- Translation — not rated
- Everyday coding — not rated
- Reasoning & maths — not rated
- Agentic work — not rated
What it costs either way
Renting the same model costs $0.4 per million input tokens and $2 per million output (OpenRouter, cheapest active endpoint, checked 2026-09-15). 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
| Machine | Price | Speed at 32k | Pay-back | |
|---|---|---|---|---|
| Strix Halo Framework Desktop, 128GB | $3,449 | 2.2 tok/s estimated | Pays back in 59 years | Run the numbers |
| DGX Spark GB10 Grace Blackwell, 128GB | $4,699 | 2.4 tok/s estimated | Pays back in 82 years | Run the numbers |
| Mac Studio M5 Max, 128GB | $5,099 | 5.3 tok/s estimated | Pays back in 67 years | Run the numbers |
| MacBook Pro M5 Max (16-inch), 128GB | $6,999 | 5.3 tok/s estimated | Pays back in 91 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
- 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.
- Maximum context
- 256k tokens (256k)
- Licence
- other (see repo)
- Sources
- source 1