Open Systems, Blockchain & Business Daily

OSBBD

AI, money and the software behind them.

Nemotron 3.5 Bolt E4B

Nemotron 3.5 Bolt E4B is an open-weight small language model from NVIDIA, released on October 23, 2026.

Developer
NVIDIA
Released
October 23, 2026
Total parameters
8B
Architecture
Dense
Context window
64K
Input
Text
License
OpenMDW License Agreement v1.1
Commercial use
Yes
Official weights, GB
16 GB
Hugging Face repository
huggingface.co
Checked on

Nemotron 3.5 Bolt E4B is a dense model with 8B parameters. NVIDIA describes it as having 4B effective parameters and builds it on Gemma 4 E4B with its own post-training, aimed at voice and device assistants. NVIDIA lists a context window of up to 64K tokens. The model takes text and produces text. The weights are released under the OpenMDW License Agreement v1.1, which allows commercial use.

The official BF16 weights on Hugging Face take about 16.0 GB. Running the model needs at least that much memory across GPUs and system RAM, plus room for the context cache; NVIDIA also publishes a 4-bit Q4_K_M GGUF build (about 6.2 GB) that needs less.

Total parameters, billions
8B
Context window, tokens
65.54K
License type
Custom license
License conditions
OpenMDW 1.1: redistributions must include the agreement and origin notices.
Weights precision
BF16
Official quantized or alternative versions
nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB; nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-DFlash
License text
raw.githubusercontent.com
Sources
PageURL
Hugging Face model cardhttps://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16/raw/main/README.md
Hugging Face weights indexhttps://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16/raw/main/model.safetensors.index.json
NVIDIA announcement (October 23, 2026)https://research.nvidia.com/labs/nemotron/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB/
License text on GitHubhttps://raw.githubusercontent.com/OpenMDW/OpenMDW/refs/heads/main/1.1/LICENSE.OpenMDW-1.1

Questions

What license does Nemotron 3.5 Bolt E4B use?
The weights are released under the OpenMDW License Agreement v1.1, which allows commercial use; redistributions must include the agreement and origin notices.
How much memory does Nemotron 3.5 Bolt E4B need?
The official BF16 weights take about 16.0 GB. NVIDIA’s Q4_K_M GGUF build is about 6.2 GB; the memory calculator checks which setups fit.
How many parameters does Nemotron 3.5 Bolt E4B have?
8B in total, which NVIDIA describes as 4B effective parameters.
What context window does Nemotron 3.5 Bolt E4B have?
NVIDIA lists a context window of up to 64K tokens for both input and output.

Sources

Every figure comes from the developer’s model card, license text and official announcements, and from the model’s Hugging Face repository metadata. Each model page lists its sources and the date they were checked; the register is rechecked every week.

OSBBD

What are you looking for?

Search by headline, topic or keyword.