GLM-4.7-Flash vs Devstral Small 2 24B
GLM-4.7-Flash scores higher on the intelligence index, 15 against 8. Both take the same machine to start: the cheapest here that runs either is the Framework Desktop, 32GB, at $1,269. On it, GLM-4.7-Flash is about 4.1× quicker: 40 tok/s against 9.7, both estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 32GB pays for itself in 96 years running GLM-4.7-Flash, and never running Devstral Small 2 24B.
| GLM-4.7-Flash | Devstral Small 2 24B | |
|---|---|---|
| Intelligence index | 15 | 8 |
| Class | Haiku-class | Below every hosted tier |
| Weights | 18 GB | 14 GB |
| Needs at 32k | 20 GB | 20 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 31.2B (3B active) | 24B |
| Max context | 198k | 384k |
| API price per 1M | $0.061 in / $0.4 out | $0.02 in / $0.1 outpriced as gpt-oss-20b |
| Licence | MIT | Apache 2.0 |
| Machines here that run it | 30 of 37 | 30 of 37 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 32GB $1,269 | Strix Halo Framework Desktop, 32GB $1,269 |
| Summarising | not rated | not rated |
| Translation | not rated | not rated |
| Everyday coding | not rated | not rated |
| Reasoning & maths | not rated | not rated |
| Agentic work | not rated | not rated |
Run GLM-4.7-Flash on the Framework Desktop, 32GB · or Devstral Small 2 24B
Ratings are coarse on purpose: they say what a model is usable for, not where it places to the decimal.
Side by side on the Framework Desktop, 32GB
The cheapest machine that runs either model is the same one, so this is the pair doing the same work on the same hardware: Strix Halo Framework Desktop, 32GB, at $1,269.
| GLM-4.7-Flash | Devstral Small 2 24B | |
|---|---|---|
| Speed at 32k | 40 tok/s estimated | 9.7 tok/s estimated |
| Pay-back on this machine | Pays back in 96 years | Never pays back |
| API cost per month | $1.25 | $0.38priced as gpt-oss-20b |
Run GLM-4.7-Flash on the Framework Desktop, 32GB · or Devstral Small 2 24B
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, 32GB. GLM-4.7-Flash pays for it sooner at every level of use: Devstral Small 2 24B never pays for it at all.
| A day's use | GLM-4.7-Flash | Devstral Small 2 24B |
|---|---|---|
| 50ka few chats a day | 961 years | Never pays back |
| 200klight assistant use | 240 years | Never pays back |
| 1Ma moderate coding-assistant day | 48 years | Never pays back |
| 4Mheavy coding with an agent | 12 years | Never pays back |
| 20Magents running most of the day | 2.4 years | Never pays backits ceiling |
The Framework Desktop, 32GB generates at most 13.5M tokens a day on Devstral Small 2 24B, 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 GLM-4.7-Flash at 20M tokens a day · or Devstral Small 2 24B
Memory is not what separates them
GLM-4.7-Flash needs 20 GB of memory at 32k of context and Devstral Small 2 24B needs 20 GB. Every machine priced here that runs one runs the other, at 32k of context. So the choice between them is what each is good at, how fast it runs and what the same work costs on an API, not what you have to buy to hold it.
GLM-4.7-Flash is also head to head with Granite 4.2 30B above it on the leaderboard and Gemma 4 12B below it. Two more models need much the same memory: Qwen3 30B-A3B Instruct 2507 and Qwen3-Coder 30B-A3B. Devstral Small 2 24B is also head to head with LFM2.5 2.6B above it on the leaderboard, Llama 3.1 8B Instruct below it and Mistral Small 3.2 24B Instruct, the last-generation Mistral nearest it in size. One more model needs much the same memory: Gemma 3 27B it.
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 GLM-4.7-Flash · every machine that runs Devstral Small 2 24B · every other match-up · both against the frontier · the quickest pay-back at each level of use