Qwen3 30B-A3B Instruct 2507 vs Qwen3-Coder 30B-A3B
Neither has a clear lead on the index.
| Qwen3 30B-A3B Instruct 2507 | Qwen3-Coder 30B-A3B | |
|---|---|---|
| Intelligence index | 10 | 10 |
| Class | Below every hosted tier | Below every hosted tier |
| Weights | 19 GB | 19 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 30.5B (3.3B active) | 30.5B (3.3B active) |
| Max context | 256k | 256k |
| API price per 1M | $0.048 in / $0.193 out | $0.07 in / $0.27 out |
| Licence | Apache 2.0 | Apache 2.0 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 32GB $1,269 | Strix Halo Framework Desktop, 32GB $1,269 |
| Summarising | good | usable |
| Translation | good | usable |
| Everyday coding | good | good |
| Reasoning & maths | usable | usable |
| Agentic work | usable | usable |
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.