# NVIDIA releases Nemotron 3.5 Bolt E4B, an 8B model with a DFlash drafter

> Original title: NVIDIA just released an E4B version (8B, 4B effective) of Nemotron 3.5 Bolt that outperforms Gemma-4 and Qwen3.5 🤯

- Source: Merve Noyan
- Published: 2026-10-23T17:31:24.000Z
- Bad Influence: https://badinfluence.news/items/b1j0owgm3dvfj274rs5uqdhim
- Original: https://x.com/mervenoyann/status/2113684730109403404

## Summary

NVIDIA has released Nemotron 3.5 Bolt E4B, an 8B-parameter model with 4B effective parameters, which Merve Noyan says outperforms Gemma-4 and Qwen3.5. The release includes a DFlash drafter for speeding up decoding, along with quantized versions from ggml and Unsloth.

## Post

NVIDIA just released an E4B version (8B, 4B effective) of Nemotron 3.5 Bolt that outperforms Gemma-4 and Qwen3.5 🤯 

it even comes with DFlash drafter for speeding up decoding ⚡️ 

comes with quants from ggml & unsloth too! https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVVRDwhWcAAM8_c.jpg&mode=thumb&exp=1794528000&sig=0529c22ffa4ff885)