magnitudedev/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark-GGUF overview
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DSpark GGUF Native NVFP4 GGUF conversion of nvidia/NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DSpark https://huggi…
Runs locally from ~1.26 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark.gguf | GGUF | GGUF | 1.26 GB | Download |
Model Details
| Model ID | magnitudedev/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark-GGUF |
|---|---|
| Author | magnitudedev |
| Pipeline | — |
| License | other |
| Base model | nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark |
| Last modified | 2026-10-15T18:18:35.000Z |
Model README
---
base_model:
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark
license: other
license_name: openmdw-1.1
license_link: https://openmdw.ai/license/1-1/
library_name: llama.cpp
tags:
- gguf
- nvfp4
- dspark
- speculative-decoding
- magnitude
inference: false
---
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DSpark GGUF
Native NVFP4 GGUF conversion of
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark
for use with Magnitude.
Converted with
at revision 620d2225cc436ab0b001e3200e590e3b286ef9ab.
Artifact
- Quantization:
NVFP4 - SHA-256:
14fcc5296ca9be2fa2156275fd1811de966835e2894729907a03cf7f80634856 - Source revision:
6d127b50ecd98562cea85d0087680b7d86091fb0
Draft metadata
dflash.attention.causal = true: the draft block uses causal attention.dflash.sample_from_anchor = false: proposals come from mask rows, starting after the anchor.dflash.attention.sliding_window = 1024on every layer.- Derived from the NVIDIA checkpoint configuration.
Run magnitudedev/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models