---

base_model:

- nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr

license: other

license_name: openmdw-1.1

license_link: https://openmdw.ai/license/1-1/

library_name: llama.cpp

tags:

- gguf

- nvfp4

- lilicorr

- speculative-decoding

- magnitude

inference: false

---

NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB LiLiCorr GGUF

NVFP4 GGUF of

nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr

for use with Magnitude.

This is the LiLiCorr draft model for speculative decoding with

nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF.

Artifact

• File: NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr.gguf
• Quantization: NVFP4
• SHA-256: 43979b5789616082984a7287660b1194421f9c2afeb1e32aff72ea95a2e82962
• Source revision: 4c6a5613b6d887194a3a5493e3a18a5b3930bb86
• GGUF from nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-GGUF

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.
• dflash.attention.sliding_window = 1024 on every layer.
• Derived from the NVIDIA checkpoint configuration.