magnitudedev/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash-GGUF overview
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash GGUF Native NVFP4 GGUF conversion of nvidia/NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash https://huggi…
Runs locally from ~1.10 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-DFlash.gguf | GGUF | GGUF | 1.10 GB | Download |
Model Details
| Model ID | magnitudedev/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash-GGUF |
|---|---|
| Author | magnitudedev |
| Pipeline | — |
| License | other |
| Base model | nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash |
| Last modified | 2026-10-06T21:58:47.000Z |
Model README
---
base_model:
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash
license: other
license_name: openmdw-1.1
license_link: https://openmdw.ai/license/1-1/
library_name: llama.cpp
tags:
- gguf
- nvfp4
- dflash
- speculative-decoding
- magnitude
---
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash GGUF
Native NVFP4 GGUF conversion of
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash
for use with Magnitude.
Converted with
at revision 9b05354ec6fb58b4e665e9a39ebc40285c015638.
Artifact
- Quantization:
NVFP4 - SHA-256:
ca3b2a765da43234524c0c83669b4f552e31f0f226c7afa509f133cfd050bc19
Draft metadata
dflash.attention.causal = false: the draft block uses bidirectional attention.dflash.sample_from_anchor = false: proposals come from mask rows, starting after the anchor.- Derived from the NVIDIA checkpoint configuration and reference implementation; verified against reference outputs.
Run magnitudedev/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models