Instructions to use HelloSun/Nemotron74ba9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use HelloSun/Nemotron74ba9 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 HelloSun/Nemotron74ba9
# Run inference directly in the terminal:
llama cli -hf HelloSun/Nemotron74ba9

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HelloSun/Nemotron74ba9
# Run inference directly in the terminal:
llama cli -hf HelloSun/Nemotron74ba9

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 HelloSun/Nemotron74ba9
# Run inference directly in the terminal:
./build/bin/llama cli -hf HelloSun/Nemotron74ba9

Use Docker

docker model run hf.co/HelloSun/Nemotron74ba9

Llama new
LM Studio
Jan
Ollama
How to use HelloSun/Nemotron74ba9 with Ollama:
```
ollama run hf.co/HelloSun/Nemotron74ba9
```
Unsloth Desktop

How to use HelloSun/Nemotron74ba9 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HelloSun/Nemotron74ba9

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": "HelloSun/Nemotron74ba9"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use HelloSun/Nemotron74ba9 with Docker Model Runner:
```
docker model run hf.co/HelloSun/Nemotron74ba9
```

Lemonade

How to use HelloSun/Nemotron74ba9 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HelloSun/Nemotron74ba9

Run and chat with the model

lemonade run user.Nemotron74ba9-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use HelloSun/Nemotron74ba9 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HelloSun/Nemotron74ba9

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 HelloSun/Nemotron74ba9

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use HelloSun/Nemotron74ba9 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HelloSun/Nemotron74ba9

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 "HelloSun/Nemotron74ba9" \
  --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"

Nemotron74ba9 / benchmarks /spec_decoding.jsonl

HelloSun

Add decode analysis (bandwidth-bound), thread sweep, speculative decoding results, optional IQ2_XXS patch

26d741f verified 5 days ago

Raw History Blame Contribute Delete

3.48 kB

{"cfg": "none", "prompt": "code", "rep": 0, "n": 200, "tg_tps": 10.909301220882378, "draft_n": null, "draft_acc": null, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
{"cfg": "none", "prompt": "code", "rep": 1, "n": 200, "tg_tps": 10.949859602440862, "draft_n": null, "draft_acc": null, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
{"cfg": "none", "prompt": "prose", "rep": 0, "n": 200, "tg_tps": 10.685328512370845, "draft_n": null, "draft_acc": null, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
{"cfg": "none", "prompt": "prose", "rep": 1, "n": 200, "tg_tps": 10.957353320133118, "draft_n": null, "draft_acc": null, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
{"cfg": "none", "prompt": "repeat", "rep": 0, "n": 129, "tg_tps": 10.949360916598376, "draft_n": null, "draft_acc": null, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
{"cfg": "none", "prompt": "repeat", "rep": 1, "n": 129, "tg_tps": 10.90838558279584, "draft_n": null, "draft_acc": null, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
{"cfg": "dflash", "prompt": "code", "rep": 0, "n": 200, "tg_tps": 11.545029531199281, "draft_n": 210, "draft_acc": 164, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
{"cfg": "dflash", "prompt": "code", "rep": 1, "n": 200, "tg_tps": 11.733808126057184, "draft_n": 210, "draft_acc": 164, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
{"cfg": "dflash", "prompt": "prose", "rep": 0, "n": 200, "tg_tps": 5.49757137187501, "draft_n": 446, "draft_acc": 124, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
{"cfg": "dflash", "prompt": "prose", "rep": 1, "n": 200, "tg_tps": 5.5349755522354975, "draft_n": 446, "draft_acc": 124, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
{"cfg": "dflash", "prompt": "repeat", "rep": 0, "n": 129, "tg_tps": 13.308025904072423, "draft_n": 114, "draft_acc": 109, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
{"cfg": "dflash", "prompt": "repeat", "rep": 1, "n": 129, "tg_tps": 13.36414743786846, "draft_n": 114, "draft_acc": 109, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
{"cfg": "ngram", "prompt": "code", "rep": 0, "n": 200, "tg_tps": 10.665492426321277, "draft_n": null, "draft_acc": null, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
{"cfg": "ngram", "prompt": "code", "rep": 1, "n": 200, "tg_tps": 13.48765469543554, "draft_n": 186, "draft_acc": 145, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
{"cfg": "ngram", "prompt": "prose", "rep": 0, "n": 200, "tg_tps": 10.277698241821534, "draft_n": null, "draft_acc": null, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
{"cfg": "ngram", "prompt": "prose", "rep": 1, "n": 200, "tg_tps": 8.9637426968019, "draft_n": 64, "draft_acc": 27, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
{"cfg": "ngram", "prompt": "repeat", "rep": 0, "n": 129, "tg_tps": 10.056218977939327, "draft_n": null, "draft_acc": null, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
{"cfg": "ngram", "prompt": "repeat", "rep": 1, "n": 129, "tg_tps": 22.175933810381558, "draft_n": 124, "draft_acc": 124, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}

	{"cfg": "none", "prompt": "code", "rep": 0, "n": 200, "tg_tps": 10.909301220882378, "draft_n": null, "draft_acc": null, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
	{"cfg": "none", "prompt": "code", "rep": 1, "n": 200, "tg_tps": 10.949859602440862, "draft_n": null, "draft_acc": null, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
	{"cfg": "none", "prompt": "prose", "rep": 0, "n": 200, "tg_tps": 10.685328512370845, "draft_n": null, "draft_acc": null, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
	{"cfg": "none", "prompt": "prose", "rep": 1, "n": 200, "tg_tps": 10.957353320133118, "draft_n": null, "draft_acc": null, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
	{"cfg": "none", "prompt": "repeat", "rep": 0, "n": 129, "tg_tps": 10.949360916598376, "draft_n": null, "draft_acc": null, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
	{"cfg": "none", "prompt": "repeat", "rep": 1, "n": 129, "tg_tps": 10.90838558279584, "draft_n": null, "draft_acc": null, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
	{"cfg": "dflash", "prompt": "code", "rep": 0, "n": 200, "tg_tps": 11.545029531199281, "draft_n": 210, "draft_acc": 164, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
	{"cfg": "dflash", "prompt": "code", "rep": 1, "n": 200, "tg_tps": 11.733808126057184, "draft_n": 210, "draft_acc": 164, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
	{"cfg": "dflash", "prompt": "prose", "rep": 0, "n": 200, "tg_tps": 5.49757137187501, "draft_n": 446, "draft_acc": 124, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
	{"cfg": "dflash", "prompt": "prose", "rep": 1, "n": 200, "tg_tps": 5.5349755522354975, "draft_n": 446, "draft_acc": 124, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
	{"cfg": "dflash", "prompt": "repeat", "rep": 0, "n": 129, "tg_tps": 13.308025904072423, "draft_n": 114, "draft_acc": 109, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
	{"cfg": "dflash", "prompt": "repeat", "rep": 1, "n": 129, "tg_tps": 13.36414743786846, "draft_n": 114, "draft_acc": 109, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
	{"cfg": "ngram", "prompt": "code", "rep": 0, "n": 200, "tg_tps": 10.665492426321277, "draft_n": null, "draft_acc": null, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
	{"cfg": "ngram", "prompt": "code", "rep": 1, "n": 200, "tg_tps": 13.48765469543554, "draft_n": 186, "draft_acc": 145, "text": "```python\nimport csv\nfrom statistics import median\nfrom typi"}
	{"cfg": "ngram", "prompt": "prose", "rep": 0, "n": 200, "tg_tps": 10.277698241821534, "draft_n": null, "draft_acc": null, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
	{"cfg": "ngram", "prompt": "prose", "rep": 1, "n": 200, "tg_tps": 8.9637426968019, "draft_n": 64, "draft_acc": 27, "text": "Token generation in Large Language Models (LLMs) is fundamen"}
	{"cfg": "ngram", "prompt": "repeat", "rep": 0, "n": 129, "tg_tps": 10.056218977939327, "draft_n": null, "draft_acc": null, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}
	{"cfg": "ngram", "prompt": "repeat", "rep": 1, "n": 129, "tg_tps": 22.175933810381558, "draft_n": 124, "draft_acc": 124, "text": "1. The quick brown fox jumps over the lazy dog near the rive"}