Nemotron120B paramspopular

NVIDIA Nemotron 3 Super 120B A12B BF16 locally

NVIDIA Nemotron 3 Super 120B A12B BF16 is an open-weight LLM from the Nemotron family with 120B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: NVIDIA A100 80GB (80 GB).

Technical facts
Parameters120B
Q4_K_M75.4 GB
Q5_K_M92.2 GB
Q8134.1 GB
FP16268.2 GB
FamilyNemotron
Last sync2026-05-12

Available quantizations

Q4_K_M
75.4GB

Acceptable. Good compromise when VRAM is limited.

Q5_K_M
92.2GB

Good quality. Sweet spot for size and precision.

Q8
134.1GB

Near-FP16 quality. Comfortable for production.

FP16
268.2GB

Reference precision. Maximum quality, doubled VRAM.

Compatible GPUs

GPUs that can run NVIDIA Nemotron 3 Super 120B A12B BF16 on a single card, ranked by VRAM headroom.

Recommended multi-GPU rigs

For NVIDIA Nemotron 3 Super 120B A12B BF16 at higher quantization or with more context, a multi-GPU rig gives more headroom.

Recommended rig

4× TITAN RTX

NVIDIA Nemotron 3 Super 120B A12B BF16 with Ubuntu, vLLM, Open WebUI and the model already downloaded.

Configure

Similar models

VRAM estimates: parameters x bits/8 plus margin. Real performance varies by engine, context length and batch size.
sync: 2026-05-12