Instructions to use EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF",
	filename="North-Mini-Code-1.0-EAGLE3.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use EntityDeletr/North-Mini-Code-1.0-EAGLE3-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 EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF
# Run inference directly in the terminal:
llama cli -hf EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF
# Run inference directly in the terminal:
llama cli -hf EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF

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 EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF
# Run inference directly in the terminal:
./llama-cli -hf EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF

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 EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF

Use Docker

docker model run hf.co/EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF

LM Studio
Jan
Ollama
How to use EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF with Ollama:
```
ollama run hf.co/EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF
```

Unsloth Studio

How to use EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF with Docker Model Runner:
```
docker model run hf.co/EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF
```

Lemonade

How to use EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EntityDeletr/North-Mini-Code-1.0-EAGLE3-GGUF

Run and chat with the model

lemonade run user.North-Mini-Code-1.0-EAGLE3-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Quantized version of AlexWortega/North-Mini-Code-1.0-EAGLE3.

Their model card is pasted as is below.

Files:

model.safetensors - original unquantized safetensors
model.gguf - unquantized bf16 GGUF
North-Mini-Code-1.0-EAGLE3.gguf - GGUF quantized to Q5_K_M

North-Mini-Code-1.0 — EAGLE-3 draft head

EAGLE-3 draft model for CohereLabs/North-Mini-Code-1.0 (cohere2_moe, 30B/3B MoE, 49 layers), trained with SpecForge (offline) for lossless speculative decoding.

Draft: 1 Llama-style decoder layer, hidden 2048, FFN 12288, draft_vocab 32000 (freq-reduced from 262144).
Aux hidden-state layers: [1, 23, 45].
Training: offline, ~8.3k code-instruction samples (magicoder-evol-instruct), 10 epochs, lr 1e-4.
Offline held-out acceptance (Σ over 7 positions): τ = 4.25 (pos-0 acc 0.71).

Serving in vLLM

Needs vLLM main + --hf-overrides '{"first_k_dense_replace":1}', and a patch adding the EAGLE3 interface (SupportsEagle3) to cohere2_moe.py. See repo notes.

vllm serve CohereLabs/North-Mini-Code-1.0 \
  --speculative-config '{"method":"eagle3","model":"<this-repo>","num_speculative_tokens":5}' \
  --hf-overrides '{"first_k_dense_replace":1}' \
  --reasoning-parser cohere_command4 --tool-call-parser cohere_command4 --enable-auto-tool-choice

Note: this draft was trained offline on HuggingFace-transformers hidden states; real vLLM acceptance is modest (~1.28) due to train/serve hidden-state representation mismatch. For best speedup, retrain online in vLLM/SpecForge so the draft matches serving-time hidden states.