Devstral Small 2 24B vs Llama 3.1 8B Instruct
Devstral Small 2 24B scores higher on the intelligence index — 8 against 7. Llama 3.1 8B Instruct is the smaller download at 4.9 GB, so it runs on cheaper hardware.
| Devstral Small 2 24B | Llama 3.1 8B Instruct | |
|---|---|---|
| Intelligence index | 8 | 7 |
| Class | Below every hosted tier | Below every hosted tier |
| Weights | 14 GB | 4.9 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 24B | 8B |
| Max context | 384k | 128k |
| API price per 1M | $0.02 in / $0.1 out | $0.02 in / $0.04 out |
| Licence | Apache 2.0 | Llama 3.1 Community License |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 32GB $1,269 | Mac mini M6, 16GB $899 |
| Summarising | not rated | good |
| Translation | not rated | usable |
| Everyday coding | not rated | usable |
| Reasoning & maths | not rated | don’t |
| Agentic work | not rated | don’t |
Ratings are coarse on purpose. Speeds and pay-back depend on the machine — open either model's page for the full list, or see both against the frontier. Context is 32k throughout.