Changes / Feeds / nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
4 changes to a tracked key since 2026-04-20, newest first. Head as last read: e5e9932441de940c9a62185c870ea5bcd4cd24e2.
GPU memory to fine-tune it, card by card: Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2026-04-28 | x_NXMC-2026-0043 | pad token unset to "<|im_end|>"; batched training masks a different id (2026-04-28).23d21acd455d -> 9de8c684c189 |
| 2026-04-21 | x_NXMC-2026-0042 breaking | the chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2026-04-21).eb24a9033590 -> 23d21acd455d |
| 2026-04-20 | x_NXMC-2026-0041 | generation defaults changed (do_sample unset to true, max_new_tokens unset to 16384, repetition_penalty unset to 1, temperature unset to 0.6); a call that does not pass these explicitly now generates differently (2026-04-20).d0e46b0fc1ec -> 43f3e65ffd90 |
| 2026-04-20 | x_NXMC-2026-0040 breaking | architectures ["Nemotron_3_Nano_Omni_30B_A3B_Reasoning"] to ["NemotronH_Nano_Omni_Reasoning_V3"]; a different class is instantiated from the same id (2026-04-20).62f3c9dfb13f -> d0e46b0fc1ec |
Pin it, and let a bot move the pin
from_pretrained("nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", revision="e5e9932441de940c9a62185c870ea5bcd4cd24e2")With the Renovate preset, a pull request moves this pin when the head moves, and links back here.
[](https://www.neurarch.com/changes-feeds/models/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16.html)