OTel-2.0-Decision-26B-A4B-4bit vs NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8
Specs, VRAM requirements and download trends — updated 10 November 2026.
farbodtavakkoli · A · Open weights
Params
25.8 B
Context
—
30d
3.2 M
apache-2.0 · commercial OK
RedHatAI · B · Open weights
Params
31.6 B
Context
262,144
30d
820 K
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | OTel-2.0-Decision-26B-A4B-4bit | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8 |
|---|---|---|
| Parameters | 25.8 B | 31.6 B |
| Architecture | Gemma4ForConditionalGeneration | NemotronHForCausalLM |
| Context length | — | 262,144 |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | 1 | — |
| Downloads 30d | 3,246,291 | 820,287 |
| Downloads all time | 3.2 M | 1.9 M |
| Quantizations on the Hub | GGUF, SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-10-06 | 2026-08-13 |
Download trend
Daily snapshots, last 19 days (23 Oct – 10 Nov)
3.2 M220 K
OTel-2.0-Decision-26B-A4B-4bit
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8
A overtook B on 28 Oct
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-3.5-Lightning-30B-A3B-FP8 · fp16 @ 256K ctx
187.6 GB / 24 GB