OTel-2.0-LLM-31B-IT vs NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit
Specs, VRAM requirements and download trends — updated 14 August 2026.
farbodtavakkoli · A · Open weights
Params
31.3 B
Context
262,144
30d
720 K
apache-2.0 · commercial OK
cyankiwi · B · Open weights
Params
127.2 B
Context
262,144
30d
168 K
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | OTel-2.0-LLM-31B-IT | NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit |
|---|---|---|
| Parameters | 31.3 B | 127.2 B |
| Architecture | Gemma4ForConditionalGeneration | NemotronHForCausalLM |
| Context length | 262,144 | 262,144 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | 1 | 7 |
| Downloads 30d | 720,422 | 167,639 |
| Downloads all time | 14.2 M | 208 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-23 | 2026-03-16 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
7.6 M165 K
OTel-2.0-LLM-31B-IT
NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit
A overtook B on 27 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
OTel-2.0-LLM-31B-IT · fp16 @ 256K ctx
290.0 GB / 24 GB
NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit · fp16 @ 256K ctx
699.9 GB / 24 GB