Instructions to use andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast 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 andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M

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 andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M

Use Docker

docker model run hf.co/andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast with Ollama:
```
ollama run hf.co/andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M
```
Unsloth Desktop

How to use andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast: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": "andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast with Docker Model Runner:
```
docker model run hf.co/andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M
```

Lemonade

How to use andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M

Run and chat with the model

lemonade run user.Nemotron-3-Nano-4B-HIPE-step-fast-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast: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 andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast: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 "andersonscode/Nemotron-3-Nano-4B-HIPE-step-fast: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"

Nemotron-3-Nano-4B-HIPE-step-fast / config.json

andersonscode

(Trained with Unsloth)

c9a248d verified 7 months ago

Raw History Blame Contribute Delete

1.71 kB

Invalid JSON:Unexpected token 'I', ...", Infinity "... is not valid JSON

{
    "architectures": [
        "NemotronHForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_head_dim": 128,
    "auto_map": {
        "AutoConfig": "configuration_nemotron_h.NemotronHConfig",
        "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
    },
    "bos_token_id": 1,
    "chunk_size": 256,
    "conv_kernel": 4,
    "torch_dtype": "bfloat16",
    "eos_token_id": 11,
    "expand": 2,
    "head_dim": 128,
    "hidden_dropout": 0.0,
    "hidden_size": 3136,
    "hybrid_override_pattern": "M-M-M-MM-M-M*-M-M*-M-M-M*-M-M-MM*-MMM-M-M-",
    "initializer_range": 0.02,
    "intermediate_size": 12544,
    "layer_norm_epsilon": 1e-05,
    "mamba_head_dim": 80,
    "mamba_hidden_act": "silu",
    "mamba_num_heads": 96,
    "mamba_proj_bias": false,
    "max_position_embeddings": 262144,
    "mlp_bias": false,
    "mlp_hidden_act": "relu2",
    "model_name": "unsloth/NVIDIA-Nemotron-3-Nano-4B",
    "model_type": "nemotron_h",
    "n_groups": 8,
    "num_attention_heads": 40,
    "num_hidden_layers": 42,
    "num_key_value_heads": 8,
    "num_logits_to_keep": 1,
    "pad_token_id": 999,
    "rescale_prenorm_residual": true,
    "residual_in_fp32": false,
    "rms_norm_eps": 1e-05,
    "sliding_window": null,
    "ssm_state_size": 128,
    "tie_word_embeddings": false,
    "time_step_floor": 0.0001,
    "time_step_limit": [
        0.0,
        Infinity
    ],
    "time_step_max": 0.1,
    "time_step_min": 0.001,
    "time_step_rank": 256,
    "unsloth_fixed": true,
    "unsloth_version": "2026.4.6",
    "use_bias": false,
    "use_cache": true,
    "use_conv_bias": true,
    "use_mamba_kernels": true,
    "vocab_size": 131072
}

	{
	"architectures": [
	"NemotronHForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_head_dim": 128,
	"auto_map": {
	"AutoConfig": "configuration_nemotron_h.NemotronHConfig",
	"AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
	},
	"bos_token_id": 1,
	"chunk_size": 256,
	"conv_kernel": 4,
	"torch_dtype": "bfloat16",
	"eos_token_id": 11,
	"expand": 2,
	"head_dim": 128,
	"hidden_dropout": 0.0,
	"hidden_size": 3136,
	"hybrid_override_pattern": "M-M-M-MM-M-M-M-M-M-M-M-M-M-MM-MMM-M-M-",
	"initializer_range": 0.02,
	"intermediate_size": 12544,
	"layer_norm_epsilon": 1e-05,
	"mamba_head_dim": 80,
	"mamba_hidden_act": "silu",
	"mamba_num_heads": 96,
	"mamba_proj_bias": false,
	"max_position_embeddings": 262144,
	"mlp_bias": false,
	"mlp_hidden_act": "relu2",
	"model_name": "unsloth/NVIDIA-Nemotron-3-Nano-4B",
	"model_type": "nemotron_h",
	"n_groups": 8,
	"num_attention_heads": 40,
	"num_hidden_layers": 42,
	"num_key_value_heads": 8,
	"num_logits_to_keep": 1,
	"pad_token_id": 999,
	"rescale_prenorm_residual": true,
	"residual_in_fp32": false,
	"rms_norm_eps": 1e-05,
	"sliding_window": null,
	"ssm_state_size": 128,
	"tie_word_embeddings": false,
	"time_step_floor": 0.0001,
	"time_step_limit": [
	0.0,
	Infinity
	],
	"time_step_max": 0.1,
	"time_step_min": 0.001,
	"time_step_rank": 256,
	"unsloth_fixed": true,
	"unsloth_version": "2026.4.6",
	"use_bias": false,
	"use_cache": true,
	"use_conv_bias": true,
	"use_mamba_kernels": true,
	"vocab_size": 131072
	}