NVIDIA-Nemotron-3.5-Bolt-E4B-4GB
★ agentic★ chat
Overview
NVIDIA's post-trained Gemma-4-E4B for local voice and device assistants - strong multi-turn tool use and instruction following in a compact Q4_K_M download, with a DFlash drafter for speculative decoding and a runtime thinking budget.
Good for
- agentic
- chat
Recommended hardware
≈ 8 GB VRAM to run this 8B model at the Q4_K_M quantization.
Fits 8 GB+ consumer GPUs (e.g. RTX 4060, GTX 1070), or CPU inference