Instructions to use smarttasks/Phi-mini-MoE-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smarttasks/Phi-mini-MoE-instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="smarttasks/Phi-mini-MoE-instruct-GGUF",
	filename="Phi-mini-MoE-instruct-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use smarttasks/Phi-mini-MoE-instruct-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 smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf smarttasks/Phi-mini-MoE-instruct-GGUF: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 smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf smarttasks/Phi-mini-MoE-instruct-GGUF: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 smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use smarttasks/Phi-mini-MoE-instruct-GGUF with Ollama:
```
ollama run hf.co/smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use smarttasks/Phi-mini-MoE-instruct-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 smarttasks/Phi-mini-MoE-instruct-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 smarttasks/Phi-mini-MoE-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for smarttasks/Phi-mini-MoE-instruct-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use smarttasks/Phi-mini-MoE-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M
```

Lemonade

How to use smarttasks/Phi-mini-MoE-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smarttasks/Phi-mini-MoE-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Phi-mini-MoE-instruct-GGUF-Q4_K_M

List all available models

lemonade list

Phi-mini-MoE-instruct-GGUF / MANIFEST.json

roenb

Upload folder using huggingface_hub

ba0df1b verified 3 days ago

Raw

History Blame Contribute Delete

5.16 kB

	{
	"schema": "smarttasks.repo_manifest/v1",
	"generated_utc": "2026-07-12T10:15:55+00:00",
	"root": "Phi-mini-MoE-instruct-GGUF",
	"file_count": 17,
	"risk_finding_count": 0,
	"classes_present": [
	"binary",
	"contextual",
	"ingestible",
	"model"
	],
	"agent_prefilter_hint": {
	"load": [
	"contextual",
	"ingestible"
	],
	"runtime_only": [
	"model"
	],
	"never_auto_execute": [
	"executable"
	],
	"quarantine": [
	"sensitive"
	]
	},
	"files": [
	{
	"path": ".gitattributes",
	"bytes": 44,
	"content_class": "binary",
	"ingest_policy": "skip",
	"sha256": "fdeb5cd638f262467f8cfa3f97d14d4071076dfbee5907ca4e3af7e50a3bd08b",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-f16.gguf",
	"bytes": 15302001184,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "ce9c9b134d52b441c39d8f08c6da8e4f400ebd3a46ec9620a5f13763908f94ae",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q2_K.gguf",
	"bytes": 3143596576,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "e6f10bfc4430199fdb3ee7ed701d4f8b645f2a87133830d52e7acf58a516e5ec",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q3_K_L.gguf",
	"bytes": 4166713888,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "9eb9bb25c8c91e95e20869d608f92e75ca8debd8cccb193b56ad414252cfb30d",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q3_K_M.gguf",
	"bytes": 3965911584,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "30f7c0b60149cbb5ade007796ec4a86d4956a0efd9ef3d08fbfd60dcbeaa18cb",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q3_K_S.gguf",
	"bytes": 3616211488,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "e704016c690c194ae7cde713b59cfbb496bb591c0adb9dbeb50134cd644c52ce",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q4_K_M.gguf",
	"bytes": 4993133088,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "0e81179712790f9b16e6ad4216acfb5af2a4711093b1176db62b86d5a1db868f",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q4_K_S.gguf",
	"bytes": 4616170016,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "16e1824f25a890ead375fd7f6476ef0813128079796286319e5594e8ffa1aefa",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q5_K_M.gguf",
	"bytes": 5735164448,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "347d9bf2de7224264483ca5fbb0517c31ff68f17264556b9ce21cd193a909a00",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q5_K_S.gguf",
	"bytes": 5411678752,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "3f9ff65f354eb55b4845cb38bca3c0ba5afdb6f7993937a9cf2f2e8f39209679",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q6_K.gguf",
	"bytes": 6771298848,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "ba87039f8adc7bb1374918f2bbfa2d54e0e386d5b03c0a30f115ea92d792cacb",
	"risk_findings": []
	},
	{
	"path": "Phi-mini-MoE-instruct-Q8_0.gguf",
	"bytes": 8135148064,
	"content_class": "model",
	"ingest_policy": "runtime_only",
	"sha256": "c81d70ddab0a4b6f9a7aec21f29d31e27c35ef776809bfdb6547516aecd29250",
	"risk_findings": []
	},
	{
	"path": "README.md",
	"bytes": 12380,
	"content_class": "contextual",
	"ingest_policy": "load_as_context",
	"sha256": "dee105da300d545e0246ce6f6aaf34ce1e20d21501e808f9d676765de73bad6b",
	"risk_findings": []
	},
	{
	"path": "registry.json",
	"bytes": 20220,
	"content_class": "ingestible",
	"ingest_policy": "load_structured",
	"sha256": "65f2ac5e951eaadd494e5b7b928ac7dfe9c3963f69cd1a9f3f0382b9d92d19f2",
	"risk_findings": []
	},
	{
	"path": "scorecard.json",
	"bytes": 15481,
	"content_class": "ingestible",
	"ingest_policy": "load_structured",
	"sha256": "d4ac8b4c4b2e297034679c6f4177d18ff1c911a4189c34226cd7cee0be813568",
	"risk_findings": []
	},
	{
	"path": "SECURITY.md",
	"bytes": 2254,
	"content_class": "contextual",
	"ingest_policy": "load_as_context",
	"sha256": "802aab06d9c5627e857a8184a4e0e5a4620d5e4a3bf39bfb890cfe805397dc14",
	"risk_findings": []
	},
	{
	"path": "SHA256SUMS",
	"bytes": 1102,
	"content_class": "binary",
	"ingest_policy": "skip",
	"sha256": "f7c62f106878078f7e490d1f305693f162f5c8d1c902f1c6a656cbcf95702f91",
	"risk_findings": []
	}
	]
	}