Model Intelligence Sheet
magnitudedev/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-DSpark-GGUF overview
NVIDIA Nemotron 3.5 Bolt 74B A9B DSpark GGUF NVFP4 GGUF DSpark drafter for nvidia/NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB GGUF https://huggingface.co/nvidia/NVID…
Runs locally from ~794.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| dspark-NVIDIA-Nemotron-3.5-Bolt-74B-A9B-NVFP4.gguf | GGUF | GGUF | 794.7 MB | Download |
Model Details
| Model ID | magnitudedev/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-DSpark-GGUF |
|---|---|
| Author | magnitudedev |
| Pipeline | — |
| License | other |
| Base model | unsloth/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF |
| Last modified | 2026-10-15T18:18:31.000Z |
Model README
---
base_model:
- unsloth/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF
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 Bolt 74B A9B DSpark GGUF
NVFP4 GGUF DSpark drafter for
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF
for use with Magnitude.
Artifact
- File:
dspark-NVIDIA-Nemotron-3.5-Bolt-74B-A9B-NVFP4.gguf - Quantization:
NVFP4 - SHA-256:
ea5dda20a11e9bb917f85b784dd6ab5270c69155cde7fd0ecbbd5e8659fab497 - GGUF from unsloth/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF (
dspark-NVIDIA-Nemotron-3.5-Bolt-74B-A9B-NVFP4.gguf)
Draft metadata
dflash.attention.causal = false: the draft block uses bidirectional attention.dflash.sample_from_anchor = true: proposal selection starts at the anchor row.tokenizer.ggml.mask_token_id = 18.- Verified against reference outputs.
Run magnitudedev/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-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