Nemotron 3.5 Lightning 30B-A3B vs Qwen3 235B-A22B Instruct 2507
Nemotron 3.5 Lightning 30B-A3B scores higher on the intelligence index — 14 against 13. Nemotron 3.5 Lightning 30B-A3B is the smaller download at 25 GB, so it runs on cheaper hardware.
| Nemotron 3.5 Lightning 30B-A3B | Qwen3 235B-A22B Instruct 2507 | |
|---|---|---|
| Intelligence index | 14 | 13 |
| Class | Below every hosted tier | Below every hosted tier |
| Weights | 25 GB | 142 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 31.6B (3B active) | 235.1B (22B active) |
| Max context | 256k | 256k |
| API price per 1M | $0.08 in / $0.2 out | $0.0875 in / $0.35 out |
| Licence | OpenMDW 1.1 | Apache 2.0 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 64GB $1,959 | Mac Studio M5 Ultra, 256GB $10,799 |
| Summarising | not rated | good |
| Translation | not rated | good |
| Everyday coding | not rated | good |
| Reasoning & maths | not rated | good |
| Agentic work | not rated | 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.