Instructions to use apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Use Docker

docker model run hf.co/apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

LM Studio
Jan
Ollama
How to use apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF with Ollama:
```
ollama run hf.co/apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4
```
Unsloth Desktop

How to use apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF with Docker Model Runner:
```
docker model run hf.co/apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4
```

Lemonade

How to use apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Run and chat with the model

lemonade run user.NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF:NVFP4" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

apolo13x commited on Aug 12

Commit

3051796

verified ·

1 Parent(s): 8a70f16

Add Nemotron 3.5 DFlash GGUF

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +41 -0
dflash-NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+dflash-NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,41 @@

+---
+license: other
+license_name: openmdw-1.1
+license_link: https://openmdw.ai/license/1-1/
+base_model: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash
+base_model_relation: quantized
+tags:
+  - gguf
+  - dflash
+  - nvfp4
+---
+# Nemotron 3.5 Lightning DFlash GGUF
+This is the GGUF conversion of NVIDIA's [Nemotron 3.5 Lightning DFlash checkpoint](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash).
+It must be paired with the original model. For example:
+```bash
+llama-server \
+  -hf ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:Q4_K_M \
+  -hfd apolo13x/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DFlash-GGUF \
+  --spec-type draft-dflash \
+  -ngl all \
+  -ngld all \
+  -fa on \
+  --temp 1.0 \
+  --top-p 0.95
+```
+NVIDIA recommends temperature `1.0` and top-p `0.95`.
+This DFlash GGUF was obtained with llama.cpp `b10373` by running:
+```bash
+python3 convert_hf_to_gguf.py \
+  dflash-hf \
+  --target-model-dir target-meta \
+  --outtype bf16 \
+  --outfile dflash-NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4.gguf
+```

dflash-NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:60071ad805c56e6cc663c5d2391d0000d50df5415b1199f963bec55ecc6164f2
+size 1185032768