Instructions to use CohereLabs/North-Mini-Code-1.0-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/North-Mini-Code-1.0-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="CohereLabs/North-Mini-Code-1.0-fp8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/North-Mini-Code-1.0-fp8")
model = AutoModelForCausalLM.from_pretrained("CohereLabs/North-Mini-Code-1.0-fp8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CohereLabs/North-Mini-Code-1.0-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CohereLabs/North-Mini-Code-1.0-fp8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CohereLabs/North-Mini-Code-1.0-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CohereLabs/North-Mini-Code-1.0-fp8

SGLang

How to use CohereLabs/North-Mini-Code-1.0-fp8 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 "CohereLabs/North-Mini-Code-1.0-fp8" \
    --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": "CohereLabs/North-Mini-Code-1.0-fp8",
		"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 "CohereLabs/North-Mini-Code-1.0-fp8" \
        --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": "CohereLabs/North-Mini-Code-1.0-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CohereLabs/North-Mini-Code-1.0-fp8 with Docker Model Runner:
```
docker model run hf.co/CohereLabs/North-Mini-Code-1.0-fp8
```

Model Card for North Mini Code

Model Summary

North Mini Code is an open weights research release of a 30B-A3B parameter model optimized for code generation, agentic software engineering, and terminal tasks.

Developed by: Cohere and Cohere Labs

Point of Contact: Cohere Labs
License: Apache 2.0
Model: North Mini Code
Model Size: 30B total; 3B active
Context length: 256K & 64K max output

For more details about this model, please check out our blog post.

Try North Mini Code

You can try out North Mini Code before downloading the weights in OpenCode and our hosted Hugging Face Space.

Evaluation

Benchmarking Methodology [CLICK TO EXPAND]

We used SWE-Bench Verified, SWE-Bench Pro, Terminal-Bench v2, and Terminal-Bench Hard to benchmark North Mini Code's agentic coding capabilities. For evaluation harnesses, we used the Swe-Agent harness v1.1.0 for SWE-Bench, and a simple ReAct harness employing a single terminal-use tool based on Harbor's Tmux session implementation for Terminal-Bench v2. For Terminal Bench Hard, we directly used Terminus-2, following the same methodology as the Artificial Analysis Intelligence Index to compare North-Mini-Code-1.0 with the other models. Additionally, we used SciCode and LiveCodeBench v6 as complex code-generation benchmarks outside of tool use.
We run each benchmark with 3 different seeds and report the average benchmark performance, using temperature=1.0 and top_p=0.95. We used publicly reported scores for competitor models, either from original reports or the Artificial Analysis Intelligence Index, where available. Additionally, Gemma4’s scores for agentic coding tasks were reported by Qwen team. For benchmark results that any public report is missing, denoted by (*) in the figure, we run them internally using the recommended model configuration.

Usage

To use our model in transformers, please use our BF16 model weights. Our FP8 checkpoint is designed to be used with vLLM and is not compatible with transformers due to our quantization algorithm.

vLLM

You can also run the model in vLLM. Please use vLLM main for North Mini Code until a new release is available, and accurate response parsing also requires installing Cohere’s melody library.

uv pip install "git+https://github.com/vllm-project/vllm.git"
uv pip install cohere_melody>=0.9.0

Then the vllm server can be started with the following command:

vllm serve CohereLabs/North-Mini-Code-1.0-fp8 \
  -tp 1 \
  --max-model-len 320000 \
  --tool-call-parser cohere_command4 \
  --reasoning-parser cohere_command4 \
  --enable-auto-tool-choice \  --moe-backend triton

Use locally deployed North Mini Code in OpenCode:

Please use OpenCode main branch until a new release is available.

# Example commands to install on linuxgit clone https://github.com/anomalyco/opencode.gitcd opencode

# Install Bun
curl -fsSL https://bun.sh/install | bash
export BUN_INSTALL="$HOME/.bun"
export PATH="$BUN_INSTALL/bin:$PATH"

# node-gyp was needed by a dependency
bun add -g node-gyp

# Install dependencies
bun install

# Build CLI
bun run --cwd packages/opencode build/usr/bin/install -m 755 \
  ./opencode/packages/opencode/dist/opencode-linux-x64/bin/opencode \
  /root/.local/bin/opencode

To use locally deployed North Mini Code in Opencode, please use this config which enables interleaved reasoning:

{
  "$schema": "https://opencode.ai/config.json",
  "model": "vllm/CohereLabs/North-Mini-Code-1.0-fp8",
  "provider": {
    "vllm": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Local vLLM server",
      "options": {
        "baseURL": "http://127.0.0.1:8000/v1",
        "apiKey": "EMPTY"
      },
      "models": {
        "North-Mini-Code-1.0": {
          "name": "North-Mini-Code-1.0",
          "interleaved": {
            "field": "reasoning"
          },
          "limit": {
            "context": 256000,
            "output": 64000
          }
        }
      }
    }
  }
}

Model Details

Input: Text only.

Output: Model generates text.

Model Architecture: North-Mini-Code-1.0 is a decoder-only Transformer-based sparse Mixture-of-Experts model. It uses an efficient attention implementation, interleaved between sliding-window attention with RoPE and global attention with no positional embeddings, in a 3:1 ratio. The feed-forward block is an MoE block with 128 experts, of which 8 are activated per token. Each expert block is an FFN block with SwiGLU activation. The router applies a sigmoid activation function to the logits before the top-k selection. We also use a single dense layer before the sparse layers. North-Mini-Code-1.0 was post-trained using a two-stage cascaded supervised fine-tuning (SFT) followed by reinforcement learning with verifiable rewards (RLVR), focusing on agentic coding. For more technical details, please check out our blog post.

Context Length: North-Mini-Code-1.0 supports a context length of 256K & 64K output length.