Devstral 2 123B vs DeepSeek-R1-Distill-Qwen-32B
Devstral 2 123B scores higher on the intelligence index, 9 against 8. The cheapest machine here that runs Devstral 2 123B is the Framework Desktop, 128GB, at $3,449. DeepSeek-R1-Distill-Qwen-32B runs on the Radeon AI PRO R9700, 32GB at $1,299, $2,150 less. The Radeon AI PRO R9700, 32GB is priced as the card alone, without the PC around it. On the Framework Desktop, 128GB, the cheapest machine here that runs both, DeepSeek-R1-Distill-Qwen-32B is about 3.1× quicker: 6.8 tok/s against 2.2, both estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 128GB pays for itself in 59 years running Devstral 2 123B, and never running DeepSeek-R1-Distill-Qwen-32B.
| Devstral 2 123B | DeepSeek-R1-Distill-Qwen-32B | |
|---|---|---|
| Intelligence index | 9 | 8 |
| Class | Below every hosted tier | Below every hosted tier |
| Weights | 75 GB | 20 GB |
| Needs at 32k | 87 GB | 28 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 125B | 32.8B |
| Max context | 256k | 128k |
| API price per 1M | $0.4 in / $2 out | $0.018 in / $0.09 outpriced as gpt-oss-20b |
| Licence | other (see repo) | MIT |
| Machines here that run it | 12 of 37 | 26 of 37 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 128GB $3,449 | AMD Radeon AI PRO R9700, 32GB $1,299card only |
Run Devstral 2 123B on the Framework Desktop, 128GB · or DeepSeek-R1-Distill-Qwen-32B on the Radeon AI PRO R9700, 32GB
Jump to: Side by side on the Framework Desktop, 128GB · How much use it takes to pay for the machine · Machines that run one and not the other · The assumptions behind both columns
Side by side on the Framework Desktop, 128GB
The table above gives each model the cheapest machine that runs it, and those are two different machines, so nothing in it is a like-for-like race. The Strix Halo Framework Desktop, 128GB is the cheapest machine here that runs both, so this is the pair doing the same work on the same hardware.
| Devstral 2 123B | DeepSeek-R1-Distill-Qwen-32B | |
|---|---|---|
| Speed at 32k | 2.2 tok/s estimated | 6.8 tok/s estimated |
| Pay-back on this machine | Pays back in 59 years | Never pays back |
| API cost per month | $7.61 | $0.34priced as gpt-oss-20b |
Run Devstral 2 123B on the Framework Desktop, 128GB · or DeepSeek-R1-Distill-Qwen-32B
How much use it takes to pay for the machine
Everything above is at 500k tokens a day. Pay-back moves with how much you actually run, so here are both models at the five levels of use the calculator names, on the Framework Desktop, 128GB. Devstral 2 123B pays for it sooner at every level of use: DeepSeek-R1-Distill-Qwen-32B never pays for it at all.
| A day's use | Devstral 2 123B | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| 50ka few chats a day | 585 years | Never pays back |
| 200klight assistant use | 146 years | Never pays back |
| 1Ma moderate coding-assistant day | 29 years | Never pays back |
| 4Mheavy coding with an agent | 9.6 yearsits ceiling | Never pays back |
| 20Magents running most of the day | 9.6 yearsits ceiling | Never pays backits ceiling |
The Framework Desktop, 128GB generates at most 3.06M tokens a day on Devstral 2 123B, so that column's figures from 4M tokens a day up are for the most it can do, not for the whole of what was asked. It generates at most 9.33M tokens a day on DeepSeek-R1-Distill-Qwen-32B, so that column's figure at 20M tokens a day is for the most it can do, not for the whole of what was asked.
Run Devstral 2 123B at 20M tokens a day · or DeepSeek-R1-Distill-Qwen-32B
Machines that run one and not the other
DeepSeek-R1-Distill-Qwen-32B needs 28 GB of memory at 32k of context and Devstral 2 123B needs 87 GB. That puts DeepSeek-R1-Distill-Qwen-32B on 14 of the 37 machines priced here that Devstral 2 123B does not, starting at $1,299.
| Machine | Price | Memory | Speed on DeepSeek-R1-Distill-Qwen-32B | Pay-back |
|---|---|---|---|---|
| AMD Radeon AI PRO R9700, 32GB | $1,299card only | 32 GB | 20 tok/s estimated | Never pays back |
| Strix Halo Corsair AI Workstation 300, 64GB | $1,700 | 64 GB | 6.8 tok/s estimated | Never pays back |
| Strix Halo Framework Desktop, 64GB | $1,959 | 64 GB | 6.8 tok/s estimated | Never pays back |
| NVIDIA GeForce RTX 5090, 32GB | $1,999card only | 32 GB | 43 tok/s estimated | Never pays back |
| Strix Halo GMKtec EVO-X2, 64GB | $2,200 | 64 GB | 6.8 tok/s estimated | Never pays back |
| Mac mini M5 Pro, 48GB | $2,299 | 48 GB | 8.1 tok/s estimated | Never pays back |
8 more, on the DeepSeek-R1-Distill-Qwen-32B page.
Devstral 2 123B is also head to head with Gemma 4 E4B above it on the leaderboard. One more model needs much the same memory: GLM-4.5-Air. DeepSeek-R1-Distill-Qwen-32B is also head to head with DeepSeek-R1-Distill-Llama-70B below it on the leaderboard. One more model needs much the same memory: Qwen3 32B.
The assumptions behind both columns
Both columns use the same usage: 500k tokens a day at 15:1 input to output, 32k of context, $0.17 per kWh, and today's API prices held flat. Speeds marked estimated are worked out from memory bandwidth rather than measured, and pay-back scales with them. Where nobody rents an open model by the token, its API prices are the nearest hosted model's, named beside them. Machines are the 37 here with a published price that are still sold. Change any of it in the calculator.
More head to head: every machine that runs Devstral 2 123B · every machine that runs DeepSeek-R1-Distill-Qwen-32B · every other match-up · both against the frontier · the quickest pay-back at each level of use