NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 vs OTel-2.0-Decision-26B-A4B-4bit
Specs, VRAM requirements and download trends — updated 10 November 2026.
farbodtavakkoli · B · Open weights
Params
25.8 B
Context
—
30d
3.2 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | OTel-2.0-Decision-26B-A4B-4bit |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 31.6 B | 25.8 B |
| Architecture | NemotronHForCausalLM | Gemma4ForConditionalGeneration |
| Context length | 262,144 | — |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 6 | 1 |
| Downloads 30d | 1,586,743 | 3,246,291 |
| Downloads all time | 11.9 M | 3.2 M |
| Quantizations on the Hub | SAFETENSORS | GGUF, SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-12-04 | 2026-10-06 |
| API input price / 1M tokens | $0.06 | not on OpenRouter |
| API output price / 1M tokens | $0.24 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.30 | not on OpenRouter |
| Cached input / 1M tokens | $0.012 | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | 14.4 | not on OpenRouter |
| AA Agentic Index | 1 | not on OpenRouter |
| Max output tokens | 235,929 | not on OpenRouter |
| API providers | 1 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
$0.30
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
3.2 M220 K
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
OTel-2.0-Decision-26B-A4B-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
OTel-2.0-Decision-26B-A4B-4bit · Q4_K_M
22.8 GB / 24 GB
OTel-2.0-Decision-26B-A4B-4bit · fp16
23.3 GB / 24 GB
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 · fp16 @ 256K ctx
221.6 GB / 24 GB