Instructions to use NIM-AI/NIM-2-Coder-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NIM-AI/NIM-2-Coder-7B with Transformers:

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

pipe = pipeline("text-generation", model="NIM-AI/NIM-2-Coder-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NIM-AI/NIM-2-Coder-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NIM-AI/NIM-2-Coder-7B 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 NIM-AI/NIM-2-Coder-7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NIM-AI/NIM-2-Coder-7B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NIM-AI/NIM-2-Coder-7B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NIM-AI/NIM-2-Coder-7B: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 NIM-AI/NIM-2-Coder-7B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NIM-AI/NIM-2-Coder-7B: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 NIM-AI/NIM-2-Coder-7B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NIM-AI/NIM-2-Coder-7B:Q4_K_M

Use Docker

docker model run hf.co/NIM-AI/NIM-2-Coder-7B:Q4_K_M

LM Studio
Jan

vLLM

How to use NIM-AI/NIM-2-Coder-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NIM-AI/NIM-2-Coder-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NIM-AI/NIM-2-Coder-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NIM-AI/NIM-2-Coder-7B:Q4_K_M

SGLang

How to use NIM-AI/NIM-2-Coder-7B 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 "NIM-AI/NIM-2-Coder-7B" \
    --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": "NIM-AI/NIM-2-Coder-7B",
		"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 "NIM-AI/NIM-2-Coder-7B" \
        --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": "NIM-AI/NIM-2-Coder-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use NIM-AI/NIM-2-Coder-7B with Ollama:
```
ollama run hf.co/NIM-AI/NIM-2-Coder-7B:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use NIM-AI/NIM-2-Coder-7B with Docker Model Runner:
```
docker model run hf.co/NIM-AI/NIM-2-Coder-7B:Q4_K_M
```

Lemonade

How to use NIM-AI/NIM-2-Coder-7B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NIM-AI/NIM-2-Coder-7B:Q4_K_M

Run and chat with the model

lemonade run user.NIM-2-Coder-7B-Q4_K_M

List all available models

lemonade list

Atomic Chat

NIM-2-Coder-7B / README.md

sujayanimneth

Upload README.md with huggingface_hub

f9fa412 verified 1 day ago

preview code

Raw History Blame Contribute Delete

2.08 kB

	---
	license: apache-2.0
	language:
	- en
	pipeline_tag: text-generation
	tags:
	- code
	- coding
	- software-engineering
	- autonomous-agent
	- gguf
	- ollama
	library_name: transformers
	---

	# NIM-2 Coder (7B)

	NIM-2 Coder is a specialized, high-density 7-billion parameter language model engineered by NIM AI for advanced software engineering, algorithmic design, and full-stack development.

	Engineered specifically to punch above its weight class on consumer hardware, NIM-2 Coder delivers complete, type-safe, production-ready code with deep architectural reasoning while running fully locally within 8 GB VRAM.

	[![GitHub](https://img.shields.io/badge/GitHub-N--I--M--AI-black?logo=github)](https://github.com/N-I-M-AI)
	[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)

	---

	## Key Highlights

	* Autonomous Code Synthesis: Writes idiomatic, complete code across Python, TypeScript/JavaScript, Rust, Go, C++, and Bash with zero placeholders.
	* Deterministic Logic & Edge Cases: Trained on multi-stage algorithmic problem decomposition, cyclic graph traversals, and strict type constraints.
	* Hardware Optimized: Packaged in high-throughput `Q4_K_M` GGUF quantization (~4.6 GB), allowing full offloading to consumer GPUs like the NVIDIA RTX 4060 (8 GB) and Apple Silicon.
	* Agentic Precision: Minimal conversational fluff—outputs immediate technical rationale followed by runnable implementations.

	---

	## Technical Specifications

	\| Parameter \| Specification \|
	\| :--- \| :--- \|
	\| Model Name \| NIM-2 Coder \|
	\| Organization \| NIM AI (`N-I-M-AI`) \|
	\| Architecture \| Dense Auto-regressive Transformer \|
	\| Parameters \| 7.6 Billion \|
	\| Context Length \| 4,096 tokens (dynamically extendable) \|
	\| Format \| `Q4_K_M` GGUF (~4.6 GB) / LoRA FP16 \|
	\| Prompt Template \| ChatML (`<\|im_start\|>`, `<\|im_end\|>`) \|

	---

	## Quickstart Guide

	### Run Directly via Ollama (Recommended)

	Pull and execute directly from Hugging Face:

	```bash
	ollama run hf.co/N-I-M-AI/NIM-2-Coder-7B:NIM-2-Coder-7B-Q4_K_M.gguf