Nemotron 3 Super
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
0warn against
Mar 22, 2026first mention
Jul 31, 2026latest mention
Why people recommend it
“we're using Nemotron-3-super with incredible success”
self-hosts at moderate scale on B300 GPUson “DeepSeek-V4-Flash Update”
“There are equally open, much more useful models out there:”
Show 1 more
“Nemotron-3-Super: 14070 tok/s prefill, ~194.5 tok/s generation”
Caveats and dissent
No one in these comments warned against it.
Often compared with
Who recommends it in their own words
Threads where it came up
- Google releases Gemma 4 open models 3 mentions
- DeepSeek-V4-Flash Update 1 mention
- Apertus – Open Foundation Model for Sovereign AI 1 mention
- Mamba-3 1 mention
Also written as Nemotron-3-Super. Data: nemotron-3-super.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 6
“we're using Nemotron-3-super with incredible success”
“There are equally open, much more useful models out there:”
“Nemotron-3-Super: 14070 tok/s prefill, ~194.5 tok/s generation”
“nemotron-3-super is at best 260 tokens/s PP.”
“Nemotron 3 Super was released recently. That's a direct competitor to gpt-oss-120b.”
“Nemotron 3 Super doesn't perform quite as well on benchmarks as the similarly sized Qwen3.5 122B A10B model, but it goes faster and is cheaper to run.”