Instructions to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX 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 Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama cli -hf Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

Use Docker

docker model run hf.co/Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

Llama new
LM Studio
Jan

vLLM

How to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

Ollama
How to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX with Ollama:
```
ollama run hf.co/Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP
```
Unsloth Desktop

How to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

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": "Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX with Docker Model Runner:
```
docker model run hf.co/Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP
```

Lemonade

How to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

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 Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP

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 "Harsha001/NVIDIA-Nemotron-3.5-Bolt-E4B-ROCmFPX:Q4_0_ROCMFP" \
  --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"

NVIDIA-Nemotron-3.5-Bolt-E4B — ROCmFPX GGUF

nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16, NVIDIA's small model post-trained from Google Gemma 4 E4B, quantized to the ROCmFPX formats, a llama.cpp fork with low-bit weight types for AMD GPUs (Vulkan and HIP/ROCm).

Start with Q6_0_ROCMFPX (6.2 GB). The 4-bit files are smaller but clearly further from the original.

These files need HarshaVardhan3002/ROCmFPX at commit b130d4995 or newer. Stock llama.cpp, LM Studio, Ollama and other ROCmFPX builds may not load them. These files have not been tested on AMD hardware yet.

Not an official NVIDIA release. All credit for the model goes to its authors.

Text only. The GGUFs here hold the language model. For images, use the vision projector (mmproj-*.gguf) from unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with --mmproj (not tested with these files).

Files and measured quality

Reference: the BF16 model. Measured on WikiText-2 test, 40 chunks of 512 tokens. KLD is the mean KL divergence of the next-token distribution from BF16 (lower is better). Same top is how often the quant picks the same next token.

File	Size	KLD	Same top
`NVIDIA-Nemotron-3.5-Bolt-E4B-Q8_0_ROCMFPX.gguf`	7.80 GB	0.0209	95.12%	8-bit
`NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K_ROCMFPX.gguf`	6.21 GB	0.0348	93.10%	Recommended. 6-bit, almost as close as 8-bit
`NVIDIA-Nemotron-3.5-Bolt-E4B-Q4_0_ROCMFP4_STRIX.gguf`	5.06 GB	0.2557	81.17%	best 4-bit, recipe tuned for Strix Halo (`gfx1151`)
`NVIDIA-Nemotron-3.5-Bolt-E4B-Q4_0_ROCMFP4_FAST.gguf`	4.05 GB	0.2783	80.25%	speed-first 4-bit (one scale per block)

The 6-bit file is named NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K_ROCMFPX.gguf so that Hugging Face lists it as a 6-bit quant. Its weights are the ROCmFPX Q6_0_ROCMFPX type, not a stock llama.cpp Q6_K, and it needs the same fork as the other files.

For a small model like this, 4-bit costs a lot more quality than 6-bit, so use the 4-bit files only when memory is tight. All four files answer a simple chat question correctly.

Not published: Q3_0_ROCMFPX (4.21 GB, KLD 0.3582) is larger than Q4_0_ROCMFP4_FAST and further from BF16.

How these were made

BF16 GGUF converted with the fork's convert_hf_to_gguf.py.
Importance matrix from the BF16 file over a general calibration text (calibration_datav3), 512-token chunks.
llama-quantize --imatrix from the BF16 file, one run per type, from HarshaVardhan3002/ROCmFPX. No tensor scales were needed (the model's weights are large enough for the ROCmFPX block scales).
Quality: the BF16 reference ran on an NVIDIA GPU with stock kernels. Each quant was decoded by the fork's CPU code to F16 and scored on the same GPU, so the numbers measure the weights only. AMD GPU kernels compute the same math in a different order, so results on an AMD GPU can differ slightly.

Run

git clone https://github.com/HarshaVardhan3002/ROCmFPX && cd ROCmFPX
cmake -B build -DGGML_VULKAN=ON          # or -DGGML_HIP=ON -DAMDGPU_TARGETS=gfx1151 (gfx1100 for RX 7900)
cmake --build build --target llama-server -j
build/bin/llama-server -m NVIDIA-Nemotron-3.5-Bolt-E4B-Q6_K_ROCMFPX.gguf -ngl 999 -fa on --jinja -c 32768