https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb Dated changes, score moves with their causes, what our workers noticed, and reviews for NVIDIA Nemotron 3.5 Bolt E4B 4GB. en Sun, 25 Oct 2026 20:48:29 +0000 https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#rev_4209 https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#rev_4209 Sun, 25 Oct 2026 00:00:00 +0000 review NVIDIA ships safetensors and GGUF only, from its verified organisation, with a SHA-256 for every file, and the documented vLLM and llama.cpp routes run no repository code. An undocumented handler.py in the BF16 repository loads with trust_remote_code. The explainability subcard covers prompt injection and the guardrails to add, and NVIDIA documents instruction-hierarchy training. Its content-safety and bias datasets are named, but no results are published. OpenMDW-1.1 and Apache 2.0 carry no use policy. Desk review, written from public documentation, pricing, terms, source and status history on 25 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#rev_4210 https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#rev_4210 Sun, 25 Oct 2026 00:00:00 +0000 review NVIDIA published the weights on 23 October 2026, and about four hours later replaced the GGUF in place with a new SHA-256, with the commit title Set GGUF context length to 65536 tokens as the only note. The card says thinking is on by default while the template defaults to off, and the BF16 card mentions a Mamba cache this model doesn't have. Nobody has opened a discussion yet, so responsiveness is untested. Desk review, written from public documentation, pricing, terms, source and status history on 25 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#rev_4211 https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#rev_4211 Sun, 25 Oct 2026 00:00:00 +0000 review The chat template is in the repository and the GGUF, tools go in the OpenAI tools array, and the card names vLLM's gemma4 parser and an asynchronous tool-result pattern. The card says thinking is on by default while the template defaults to off. Independent results cover instruction following only (Artificial Analysis IFBench 0.611, reasoning variant). The BFCL-v3 figure of 68.5 is NVIDIA's own run. Desk review, written from public documentation, pricing, terms, source and status history on 25 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#rev_4212 https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#rev_4212 Sun, 25 Oct 2026 00:00:00 +0000 review NVIDIA's Q4_K_M GGUF is 6.18 GB and the listing puts it at about 8 GB of memory. NVIDIA reports 3.1 to 5.0 GB of VRAM in use, its own measurement. It's free and ungated, with commercial use allowed under OpenMDW-1.1 and Apache 2.0 for the Gemma 4 base. llama.cpp, vLLM, Transformers, SGLang, Ollama and LM Studio carry it. Desk review, written from public documentation, pricing, terms, source and status history on 25 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Nemotron 3.5 Bolt E4B 4GB is NVIDIA's open-weight small language model for local voice assistants, interactive characters and device agents, post-trained from Google's Gemma 4 E4B, with 8B parameters (4B effective) and a 64K-token context.