All models

Llama-3.3-Nemotron-Super-49B-v1.5

byNVIDIANVIDIA· 25 Jul 2025
General purpose

Nvidia is not just one of the few companies that still use Llama as a base model, it is also one of the few American model providers with a cadence and quality that matches Chinese companies, as this release proves yet again. Interestingly, it is way less censored than its predecessor as evaluated by SpeechMap:

Specs
Params49B
LicenseNVIDIA Open Model License
Similarity · VAIL
VAIL
VAIL Fingerprint
00b5:0158:0291:03a2:079d:1144:2663:624b

Explore other models with behavioral similarity to Llama-3.3-Nemotron-Super-49B-v1.5.

Adoption · Hugging Face
RAM @ 30d
Relative Adoption Metric: 0.01×. Below benchmark. Measured at 30 days.
Hugging Face Downloads
16.3K
last 30d
2M
all time
HF Likes
235

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Related Models