Nemotron
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
2warn against
Jun 11, 2026first mention
Oct 30, 2026latest mention
Why people recommend it
“start with Qwen3.6, Google's Gemma4, OpenAI's gpt-oss-20b or Nvidia's Nemotron”
“it works well”
built a cross-platform live captioning appon “Transcribe.cpp”
Show 1 more
“Olmo and to a lesser extent Nemotron are what you should look at”
Caveats and dissent
“It's only good because it's free.”
“Yesterday I used the latest one on OpenRouter and it was bad - worse than StepFun”
Often compared with
Who recommends it in their own words
Threads where it came up
- Show HN: Cerebellum – small model on the robot, big model for what it can't undo 1 mention
- Nvidia Nemotron 3.5 Bolt 74B-A9B 1 mention
- Qwen3.8-Max: A New Bar for Coding and Cowork 1 mention
- Nvidia DGX Spark as a daily driver 1 mention
- Transcribe.cpp 1 mention
- Apertus – Open Foundation Model for Sovereign AI 1 mention
Data: nemotron.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 7
“We used Nemotron on the Nebius Token Factory.”
“It's only good because it's free.”
“start with Qwen3.6, Google's Gemma4, OpenAI's gpt-oss-20b or Nvidia's Nemotron”
“nemotron is decent”
“it works well”
“Yesterday I used the latest one on OpenRouter and it was bad - worse than StepFun”
“Olmo and to a lesser extent Nemotron are what you should look at”