Understand this story
NVIDIA releases the on-device small model Nemotron-3.5-Bolt-E4B. A report on October 23, 2026 states that the model can run locally on devices with 6GB of memory, targeting on-device devices such as phones; it is trained based on Gemma 4, supports vision, and Unsloth simultaneously provides the GGUF file and a guide link. NVIDIA says it targets scenarios such as local assistants, interactive characters, and robots that can converse and call tools. A follow-up report on October 24 states that the model has 8B total parameters, 4B effective parameters, and a 64K context, and is post-trained using only reinforcement learning based on Google Gemma 4 E4B; the Q4_K_M version occupies 3.1 to 4.3 GB of VRAM on RTX and can run on GeForce RTX, Jetson, and DGX Spark. The report also states that in NVIDIA's own testing, it leads Gemma 4 E4B, Qwen3.5-4B, and Nemotron 3 Nano 4B in 15 of 21 benchmarks, but Tau2-Bench is 55.1, trailing Qwen3.5-4B's 75.1.
AI-generated from public reports
Latest development · Report
NVIDIA releases Nemotron 3.5 Bolt E4B 4GB open-source small modelDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 24
MarkTechPost
NVIDIA releases Nemotron 3.5 Bolt E4B 4GB open-source small model
NVIDIA releases Nemotron 3.5 Bolt E4B 4GB open-source small language model, aimed at local voice assistants, game NPCs, and robot interfaces, post-trained with reinforcement learning only based on Google Gemma 4 E4B. The model has 8B total parameters, 4B effective parameters, and 64K context; the Q4_K_M version uses 3.1 to 4.3 GB of VRAM on RTX and can run on GeForce RTX, Jetson, and DGX Spark. In NVIDIA's own testing, it leads Gemma 4 E4B, Qwen3.5-4B, and Nemotron 3 Nano 4B on 15 of 21 benchmarks, but scores 55.1 on Tau2-Bench, behind Qwen3.5-4B's 75.1.
Oct 23
UnslothFirst-partySelected
NVIDIA releases Nemotron-3.5-Bolt-E4B, which can run locally on 6GB of memory
NVIDIA releases Nemotron-3.5-Bolt-E4B, which can run locally on devices with 6GB of memory, targeting on-device devices such as phones. The model is trained based on Gemma 4, supports vision, and Unsloth also provides GGUF files and a guide link. NVIDIA says it targets scenarios such as local assistants, interactive characters, and robots that can converse and call tools.
Heat trend for this story
- Current
- 6
- Period peak
- 17 Oct 24 13:00
- 24-hour change
- -50%
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.