NVIDIA releases Nemotron 3.5 Bolt E4B 4GB, an open small model targeting 4GB of VRAM
NVIDIA released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B. It targets local voice assistants, game characters and robots, with a footprint of about 4GB of VRAM on RTX and Jetson hardware.
NVIDIA has released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B, according to a MarkTechPost report published October 23, 2026. The model targets about 4GB of VRAM on RTX and Jetson hardware.
Key details
- Model: Nemotron 3.5 Bolt E4B 4GB
- Base: post-trained from Gemma 4 E4B
- Openness: released as an open model
- Hardware target: about 4GB of VRAM on RTX and Jetson
- Intended uses: local voice assistants, game characters and robots
What this means
The release pairs an open small model with a roughly 4GB VRAM target. That places it on NVIDIA's RTX GPUs and Jetson devices, so the use cases listed (voice agents, game characters, robots) can run on local hardware rather than only through hosted inference.
Related Articles
Block announces Dessa, a speech-to-speech model trained from scratch on human conversation
Block announced Dessa, a speech-to-speech AI model it says was trained "from scratch on nothing but human conversation." The team says it can run locally on a MacBook Pro M4 Max "or better," and early access will go to a small group of AI safety researchers.
Hugging Face releases Carbon-X, a 14B-parameter open model that answers natural-language questions about DNA
Hugging Face released Carbon-X, a 14-billion-parameter open model that takes DNA sequences and English questions and returns conversational answers. It was trained on 300 billion tokens and is designed to run locally. Its developers say it has not yet been validated with wet lab experiments.
iFLYTEK releases Spark X2.6, a 293B-A30B MoE model trained on domestic compute
At its 1024 developer festival, iFLYTEK released Spark X2.6, a 293B-A30B mixture-of-experts model trained on domestic compute. The company also open-sourced the on-device Spark X2.6-4B and debuted the SparkAudio 1.0 speech model.
NVIDIA expands Cosmos with world model training tools, simulation checkpoints and Data Factory blueprints
NVIDIA has expanded the Cosmos platform with new training tools, simulation checkpoints and Cosmos Data Factory blueprints. The company says Cosmos ranks in the top five on six different open model leaderboards.
Comments
Loading...