Qwen3.8 27B vs Inkling Small
Qwen3.8 27B scores higher on the intelligence index — 34 against 26. Qwen3.8 27B is the smaller download at 16 GB, so it runs on cheaper hardware.
| Qwen3.8 27B | Inkling Small | |
|---|---|---|
| Intelligence index | 34 | 26 |
| Class | Sonnet-class | Haiku-class |
| Weights | 16 GB | 163 GB |
| Quantisation | Q4_K_M | UD-Q4_K_M |
| Parameters | 27.8B | 266B (12B active) |
| Max context | 256k | 1024k |
| API price per 1M | $0.32 in / $2.5 out | $0.45 in / $1.2 out |
| Licence | Apache 2.0 | Apache 2.0 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 32GB $1,269 | Mac Studio M5 Ultra, 256GB $10,799 |
| 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 |
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.