Custom Comparison
Compare 2 AI Models
NVIDIA Nemotron 3.5 Lightning 30B A3b Nvfp4 vs Granite 4.1 8B
NVIDIA Nemotron 3.5 Lightning 30B A3b Nvfp4NVIDIA
Granite 4.1 8BIBM
Up to 3 models. Every selection is in the address bar, so the comparison is a link you can send.
Interactive Comparison
Loading chart...
Open weights — free to self-host | $0.05 / $0.10 per million tokens | |
|---|---|---|
| Identity | ||
| Developer | NVIDIA | IBM |
| Released | Aug 2026 | Apr 2026 |
| Status | Open weights | — |
| Licence | OpenMDW-1.1 | Apache 2.0 |
| Self-hostable | Yes — weights at nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 on Hugging Face | Yes |
| Cost | ||
| Blended $/1M tokensinput × 0.75 + output × 0.25 | — | $0.063 / 1M tokens |
| Input price | — | $0.050 / 1M tokens |
| Output price | — | $0.100 / 1M tokens |
| Capacity | ||
| Context window | 1M tokens | 131.1K tokens |
| Measured quality | ||
| LMArena Elo | 1349 (checked Oct 2026) | 1304 (checked Oct 2026) |
| LMArena rank | Rank 215 | Rank 281 |
| Elo per dollarLMArena Elo ÷ blended $/1M tokens | — | 20864 |
