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

Libraries

How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-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 prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

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 prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

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 prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

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": "prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-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 prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

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 prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M

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 "prithivMLmods/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:Q4_K_M" \
  --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-GGUF

NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 is NVIDIA's full-precision small language model, post-trained from Google's Gemma-4-E4B-it (8B total, 4B effective parameters), aimed at fast local voice and device assistants, interactive personas and embedded or edge interfaces. It keeps Gemma's conversational strengths and improves multi-turn tool use, instruction following and input grounding, with low memory use and low time to first token. Post-training was multi-environment reinforcement learning (GRPO, asynchronous, with NeMo RL and NeMo Gym) over instruction following, multi-step tool use, multi-turn conversation and structured-output environments. The model is text-in, text-out, with up to 64K tokens of input and output. It has chat-template switches for thinking (enable_thinking) and for a conversational_mode that gives concise, less formatted replies suited to spoken use, plus a documented client for capping the thinking budget at runtime. Against Gemma-4-E4B-it, Qwen3.5-4B and Nemotron-3-Nano-4B, measured by NVIDIA under NeMo Gym, it leads the BF16 group on most rows, including MultiChallenge (53.10), RoleBench (67.05), IHEval (84.79), IFBench (63.79) and RelyToolBench (63.16). Qwen3.5-4B is ahead on Tau2-Bench (75.06 vs 55.10), RULER at 64K, LongBench v2, BFCL-v3 and ToolSandbox, and Gemma leads EQ-Bench v3. The card also reports Q4_K_M results for the companion 4 GB build, which stay close to the BF16 scores. It is served with vLLM (v0.31.0) using the Gemma-4 tool and reasoning parsers, and a companion DFlash drafter is offered for speculative decoding. The card says this BF16 release is intended mainly for customization, post-training, quantization and research rather than direct production inference, and points to the Q4_K_M build for deployment. It is released under the OpenMDW-1.1 license, and the card notes the model was post-trained on Gemma 4.

Model Files

File Name	Quant Type	File Size	File Link	Description
NVIDIA-Nemotron-3.5-Bolt-E4B.BF16.gguf	BF16	15.1 GB	Link	Full BF16 weights. Highest quality, largest file size.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q2_K.gguf	Q2_K	4.4 GB	Link	Lowest quality, smallest size, good for extreme low RAM availability.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q3_K_L.gguf	Q3_K_L	5.02 GB	Link	Lower quality but usable, good for low RAM availability.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q3_K_M.gguf	Q3_K_M	4.85 GB	Link	Low quality.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q3_K_S.gguf	Q3_K_S	4.65 GB	Link	Lowest of the Q3 variants, very low RAM usage.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q4_0.gguf	Q4_0	5.19 GB	Link	Standard 4-bit quantization, older format but widely supported.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q4_K_M.gguf	Q4_K_M	5.34 GB	Link	Good quality, default size for most use cases, recommended.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q4_K_S.gguf	Q4_K_S	5.2 GB	Link	Slightly lower quality with more space savings, recommended.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q5_0.gguf	Q5_0	5.69 GB	Link	Standard 5-bit quantization, older format but widely supported.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q5_K_M.gguf	Q5_K_M	5.76 GB	Link	High quality, recommended.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q5_K_S.gguf	Q5_K_S	5.69 GB	Link	High quality, recommended.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q6_K.gguf	Q6_K	6.22 GB	Link	Very high quality, near perfect, recommended.
NVIDIA-Nemotron-3.5-Bolt-E4B.Q8_0.gguf	Q8_0	8.01 GB	Link	Extremely high quality, generally unneeded but max available quant.
NVIDIA-Nemotron-3.5-Bolt-E4B.mmproj-bf16.gguf	mmproj-bf16	992 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.

Q4_K_M Test Run

Tested NVIDIA-Nemotron-3.5-Bolt-E4B.Q4_K_M.gguf on an NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with 96 GB of VRAM, using llama-cli with full GPU offloading.

Performance Metrics

Metric	Value
Average Prompt Processing Speed	434.22 tokens/s
Average Generation Speed	189.54 tokens/s
Total Wall Time	44.1 seconds
Context Length	8,192 tokens
KV Cache (K)	`q8_0`
GPU	NVIDIA RTX PRO 6000 Blackwell Server Edition
GPU VRAM Capacity	96 GB
Peak GPU VRAM Usage	3.76 GiB
Peak GPU Utilization	85%
GPU Layers Offloaded	99 (`-ngl 99`)
Random Seed	42
Speculative Decoding	Disabled
Test Runs	5

Test Shots

Shot	Test
Shot 1	C: Insert Node at End of Singly Linked List
Shot 2	Jogger and Train Passing Time
Shot 3	Two Pipes Filling a Tank
Shot 4	Students in Examination Rooms
Shot 5	Father and Son Ages

Run Inference

./build/bin/llama-cli \
  -m /path/to/models/NVIDIA-Nemotron-3.5-Bolt-E4B.Q4_K_M.gguf \
  -ngl 99 \
  -c 8192 \
  --cache-type-k q8_0 \
  --seed 42 \
  -n 8192 \
  -st \
  -p "Your prompt here"

Performance results reflect this specific hardware and inference configuration. Actual throughput may vary depending on the prompt, model, software build, and runtime settings.