NVIDIA

About NVIDIA

NVIDIA develops computing hardware, AI software and model resources. Its Nemotron collection includes models and supporting training or deployment resources for reasoning and agent workflows. Model architecture, quantization and execution hardware remain separate conditions when interpreting a recorded run.

Focus

AI computing and software
Nemotron model development
Training and inference resources

Projects and interfaces

Nemotron
model family
NVIDIA's published model collection for language, reasoning and related agent tasks.
NeMo model-development resources
training tools
Supporting libraries and training resources released alongside Nemotron model work.

Scope and limitations

A provider's model description and hardware claims are separate from Sigma5C's dated observations.

Official references

NVIDIA AI models. Checked 2026-11-02.
NVIDIA Nemotron release information. Checked 2026-11-02.

Models

181 named catalog records. These are name and distribution records, not a count of distinct model architectures.

Llama 3.3 Nemotron Super 49B V1.5
llama3-chatqa
llama3-chatqa:70b
llama3-chatqa:70b-v1.5
llama3-chatqa:70b-v1.5-fp16
llama3-chatqa:70b-v1.5-q2_K
llama3-chatqa:70b-v1.5-q3_K_L
llama3-chatqa:70b-v1.5-q3_K_M
llama3-chatqa:70b-v1.5-q3_K_S
llama3-chatqa:70b-v1.5-q4_0
llama3-chatqa:70b-v1.5-q4_1
llama3-chatqa:70b-v1.5-q4_K_M
llama3-chatqa:70b-v1.5-q4_K_S
llama3-chatqa:70b-v1.5-q5_0
llama3-chatqa:70b-v1.5-q5_1
llama3-chatqa:70b-v1.5-q5_K_M
llama3-chatqa:70b-v1.5-q5_K_S
llama3-chatqa:70b-v1.5-q6_K
llama3-chatqa:70b-v1.5-q8_0
llama3-chatqa:8b
llama3-chatqa:8b-v1.5
llama3-chatqa:8b-v1.5-fp16
llama3-chatqa:8b-v1.5-q2_K
llama3-chatqa:8b-v1.5-q3_K_L
llama3-chatqa:8b-v1.5-q3_K_M
llama3-chatqa:8b-v1.5-q3_K_S
llama3-chatqa:8b-v1.5-q4_0
llama3-chatqa:8b-v1.5-q4_1
llama3-chatqa:8b-v1.5-q4_K_M
llama3-chatqa:8b-v1.5-q4_K_S
llama3-chatqa:8b-v1.5-q5_0
llama3-chatqa:8b-v1.5-q5_1
llama3-chatqa:8b-v1.5-q5_K_M
llama3-chatqa:8b-v1.5-q5_K_S
llama3-chatqa:8b-v1.5-q6_K
llama3-chatqa:8b-v1.5-q8_0
llama3-chatqa:latest
llama3-chatqa:latest-128k
llama3-chatqa:latest-16k
llama3-chatqa:latest-32k
llama3-chatqa:latest-64k
nemotron
Nemotron 3 Nano 30B A3B
Nemotron Nano 12B 2 VL
Nemotron Nano 9B V2
nemotron-3-nano
nemotron-3-nano:30b
nemotron-3-nano:30b-a3b
nemotron-3-nano:30b-a3b-fp16
nemotron-3-nano:30b-a3b-mlx
nemotron-3-nano:30b-a3b-mlx-bf16
nemotron-3-nano:30b-a3b-mxfp8
nemotron-3-nano:30b-a3b-nvfp4
nemotron-3-nano:30b-a3b-q4_K_M
nemotron-3-nano:30b-a3b-q8_0
nemotron-3-nano:30b-cloud
nemotron-3-nano:30b-mlx
nemotron-3-nano:4b
nemotron-3-nano:4b-bf16
nemotron-3-nano:4b-mlx
nemotron-3-nano:4b-mlx-bf16
nemotron-3-nano:4b-mxfp8
nemotron-3-nano:4b-nvfp4
nemotron-3-nano:4b-q4_K_M
nemotron-3-nano:4b-q8_0
nemotron-3-nano:latest
nemotron-3-super
nemotron-3-super-free
nemotron-3-super:120b
nemotron-3-super:120b-a12b
nemotron-3-super:120b-a12b-bf16
nemotron-3-super:120b-a12b-q4_K_M
nemotron-3-super:120b-a12b-q8_0
nemotron-3-super:cloud
nemotron-3-super:latest
nemotron-3-ultra
nemotron-3-ultra-free
nemotron-3-ultra:cloud
nemotron-3.5-bolt
nemotron-3.5-bolt:74b-a9b
nemotron-3.5-bolt:74b-a9b-iq2
nemotron-3.5-bolt:e4b
nemotron-3.5-bolt:e4b-bf16
nemotron-3.5-bolt:e4b-mlx-bf16
nemotron-3.5-bolt:e4b-mxfp8
nemotron-3.5-bolt:e4b-nvfp4
nemotron-3.5-bolt:e4b-q4_K_M
nemotron-3.5-bolt:e4b-q8_0
nemotron-3.5-bolt:latest
nemotron-3.5-lightning
nemotron-3.5-lightning-free
nemotron-3.5-lightning:30b
nemotron-3.5-lightning:30b-a3b
nemotron-3.5-lightning:30b-a3b-bf16
nemotron-3.5-lightning:30b-a3b-mlx
nemotron-3.5-lightning:30b-a3b-mlx-bf16
nemotron-3.5-lightning:30b-a3b-mxfp8
nemotron-3.5-lightning:30b-a3b-nvfp4
nemotron-3.5-lightning:30b-a3b-q4_K_M
nemotron-3.5-lightning:30b-a3b-q8_0
nemotron-3.5-lightning:30b-mlx
nemotron-3.5-lightning:latest
nemotron-3.5-super
nemotron-3.5-super-vl-free
nemotron-3.5-super:120b
nemotron-3.5-super:120b-a12b
nemotron-3.5-super:120b-a12b-bf16
nemotron-3.5-super:120b-a12b-mlx-bf16
nemotron-3.5-super:120b-a12b-mxfp8
nemotron-3.5-super:120b-a12b-nvfp4
nemotron-3.5-super:120b-a12b-q4_K_M
nemotron-3.5-super:120b-a12b-q8_0
nemotron-3.5-super:latest
nemotron-cascade-2
nemotron-cascade-2:30b
nemotron-cascade-2:30b-a3b
nemotron-cascade-2:30b-a3b-mlx
nemotron-cascade-2:30b-a3b-mlx-bf16
nemotron-cascade-2:30b-a3b-mxfp8
nemotron-cascade-2:30b-a3b-nvfp4
nemotron-cascade-2:30b-a3b-q4_K_M
nemotron-cascade-2:30b-mlx
nemotron-cascade-2:latest
nemotron-mini
nemotron-mini:4b
nemotron-mini:4b-instruct-fp16
nemotron-mini:4b-instruct-q2_K
nemotron-mini:4b-instruct-q3_K_L
nemotron-mini:4b-instruct-q3_K_M
nemotron-mini:4b-instruct-q3_K_S
nemotron-mini:4b-instruct-q4_0
nemotron-mini:4b-instruct-q4_1
nemotron-mini:4b-instruct-q4_K_M
nemotron-mini:4b-instruct-q4_K_S
nemotron-mini:4b-instruct-q5_0
nemotron-mini:4b-instruct-q5_1
nemotron-mini:4b-instruct-q5_K_M
nemotron-mini:4b-instruct-q5_K_S
nemotron-mini:4b-instruct-q6_K
nemotron-mini:4b-instruct-q8_0
nemotron-mini:latest
nemotron-mini:latest-128k
nemotron-mini:latest-16k
nemotron-mini:latest-32k
nemotron-mini:latest-64k
nemotron-mini:latest-8k
nemotron:70b
nemotron:70b-instruct-fp16
nemotron:70b-instruct-q2_K
nemotron:70b-instruct-q3_K_L
nemotron:70b-instruct-q3_K_M
nemotron:70b-instruct-q3_K_S
nemotron:70b-instruct-q4_0
nemotron:70b-instruct-q4_1
nemotron:70b-instruct-q4_K_M
nemotron:70b-instruct-q4_K_S
nemotron:70b-instruct-q5_0
nemotron:70b-instruct-q5_1
nemotron:70b-instruct-q5_K_M
nemotron:70b-instruct-q5_K_S
nemotron:70b-instruct-q6_K
nemotron:70b-instruct-q8_0
nemotron:latest
nemotron3
nemotron3:33b
nemotron3:33b-bf16
nemotron3:33b-mlx
nemotron3:33b-mlx-bf16
nemotron3:33b-mxfp8
nemotron3:33b-nvfp4
nemotron3:33b-q4_K_M
nemotron3:33b-q8
nemotron3:latest
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
nvidia/nemotron-3-super-120b-a12b:free
nvidia/nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b:free
nvidia/nemotron-3.5-content-safety
nvidia/nemotron-3.5-content-safety:free
nvidia/nemotron-3.5-super-vl
nvidia/switchyard

Model families

Llama (catalog grouping)
Nemotron (catalog grouping)
nemotron-3-nano
nemotron-3-super

Observations

Browse the Observatory