NVIDIA releases Nemotron 3.5 Bolt E4B, a small open model for local use
Article timeline
The articles in this story. Times are ET.
Google GemmaOfficialNVIDIA releases Nemotron 3.5 Bolt E4B 4GB, a small open model for local assistantsAIinteractive characters and robots that converse and use tools. The post says the model runs locally on Jetson Orin Nano 8GB, alongside NVIDIA Cosmos for vision, in a demo with Reachy Mini.
ollamaOfficialOllama lists recent cloud and local model updates from the past two weeksAIOllama lists recent cloud models including Beam, Muse-spark-open, MiniMax-m3.1-flash, Mistral-large-4, DeepSeek-v4.1-flash:1017, and Clef. Local models include Bonsai-2, EmbeddingGemma-2, Flint, Nemotron-3.5-bolt, Nemotron-3.5-super, and Phonon for text-to-speech. Users can run any of them with ollama run <model_name> after installing Ollama.
- MarkTechPostNewsNVIDIA releases Nemotron 3.5 Bolt E4B, a small open model for local voice agents
AINVIDIA has released Nemotron 3.5 Bolt E4B, an open small language model for local voice assistants, game characters and robot interfaces. Its Q4_K_M build used 3.1 to 4.3 GB VRAM on RTX in NVIDIA tests, and NVIDIA reports top scores on 15 of 21 benchmarks against Gemma 4 E4B, Qwen3.5-4B and Nemotron 3 Nano 4B. The article notes it trails Qwen3.5-4B on Tau2-Bench, 55.1 versus 75.1, and that the GGUF file is 6.18 GB.
- ollamaOfficialNvidia's Nemotron 3.5 Bolt E4B 4GB model now available on Ollama
AIOllama says Nvidia's Nemotron 3.5 Bolt E4B 4GB, a small open model, is now available on its platform. Nvidia and Ollama position it for local assistants, interactive characters and robots that hold conversations and use tools.
merveXNVIDIA releases Nemotron 3.5 Bolt E4B, an 8B model with a DFlash drafterAINVIDIA 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.
- ollamaOfficialNemotron 3.5 Bolt, a small vision-language model, is live on Ollama
AINVIDIA's Nemotron 3.5 Bolt is now available on Ollama, according to Ollama's X post. The small vision-language model is built for fast local conversations, image understanding, and tool use, and it supports a 128K-token context window.
Unsloth AIOfficialPickNVIDIA releases Nemotron-3.5-Bolt-E4B, a small model that runs on 6GB RAMAINVIDIA releases Nemotron-3.5-Bolt-E4B, a small open model that Unsloth says runs locally on 6GB RAM and edge devices such as phones. The model is trained on Gemma 4 and supports vision, with GGUF files and a guide now available from Unsloth. NVIDIA says the model is built for local assistants and robots that handle conversation and tool use.
NVIDIA AIOfficialPickNVIDIA releases Nemotron 3.5 Bolt E4B 4GB, a small open model for local useAINVIDIA has made Nemotron 3.5 Bolt E4B 4GB available now as a small open model for local assistants, interactive characters, and robots that converse and use tools. A demo shows Reachy Mini chatting and moving, with Bolt handling conversation and NVIDIA Cosmos handling vision, both running locally on a Jetson Orin Nano 8GB.
