NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8

Checkpointnvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8Model card indexedModel card

Support summary

NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8 is a checkpoint published by NVIDIA, built on the NemotronHPuzzleForCausalLM architecture. No indexed engine release, recipe, or architecture listing documents support yet. That does not mean the model is incompatible.

Configured context: 262,144 tokens
License: openmdw-1.1

Hugging Face model card

Publisher: NVIDIA
Task: text generation
License: openmdw-1.1
Library: transformers
Architecture: NemotronHPuzzleForCausalLM
Weight tensor elements: 78.3B
Tensor types: F32, BF16, F8_E4M3
Quantization: modelopt
Configured context: 262,144 tokens
Languages: en, fr, es, it, de, ja, zh
Base models: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Weight access: Public
Repository created: 2026-06-24

Source 1 Source 2 Source 3Reviewed 2026-09-05

Model notes and sources

Engine support

3 engines

Engine support for NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-FP8
Engine	Release	Evidence scope	Last known supported
vLLM	`0.28.0`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLang	`0.5.19`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM	`1.2.1`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1