Instructions to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model with Transformers:

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

pipe = pipeline("text-generation", model="KrynexLabs/KrynexAI-1.4-150M-Mobile-Model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KrynexLabs/KrynexAI-1.4-150M-Mobile-Model")
model = AutoModelForCausalLM.from_pretrained("KrynexLabs/KrynexAI-1.4-150M-Mobile-Model", device_map="auto")

Transformers.js

How to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'KrynexLabs/KrynexAI-1.4-150M-Mobile-Model');

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model 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 KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KrynexLabs/KrynexAI-1.4-150M-Mobile-Model: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 KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M

Use Docker

docker model run hf.co/KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KrynexLabs/KrynexAI-1.4-150M-Mobile-Model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KrynexLabs/KrynexAI-1.4-150M-Mobile-Model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M

SGLang

How to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model 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 "KrynexLabs/KrynexAI-1.4-150M-Mobile-Model" \
    --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": "KrynexLabs/KrynexAI-1.4-150M-Mobile-Model",
		"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 "KrynexLabs/KrynexAI-1.4-150M-Mobile-Model" \
        --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": "KrynexLabs/KrynexAI-1.4-150M-Mobile-Model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model with Ollama:
```
ollama run hf.co/KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model with Docker Model Runner:
```
docker model run hf.co/KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M
```

Lemonade

How to use KrynexLabs/KrynexAI-1.4-150M-Mobile-Model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KrynexLabs/KrynexAI-1.4-150M-Mobile-Model:Q4_K_M

Run and chat with the model

lemonade run user.KrynexAI-1.4-150M-Mobile-Model-Q4_K_M

List all available models

lemonade list

Atomic Chat

KrynexAI 1.4

KrynexAI 1.4 is a compact, ultra-lightweight 150M-parameter language model designed for high-efficiency text generation, fast inference, and on-device deployment.

🧠 Model Summary

KrynexAI 1.4 features an optimized Llama-based architecture trained on a multi-trillion token mix of web content, code, and educational data. It provides strong base capabilities in reasoning, instruction following, and general text processing while maintaining a minimal memory footprint (~270 MB weights).

Architecture: Llama-based Transformer Decoder
Parameters: ~150M
Context Window: 8,192 tokens
Precision: bfloat16 / fp16

🚀 Quickstart & Usage

pip install transformers

Basic Inference (Python)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
checkpoint = "KrynexLabs/KrynexAI-1.4-150M-Mobile-Model"
device = "cuda" if torch.cuda.is_available() else "cpu"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(
    checkpoint, 
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
inputs = tokenizer.encode("Gravity is", return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📌 Performance Benchmarks

Metric	KrynexAI 1.4
HellaSwag	42.1
ARC (Average)	43.9
PIQA	68.4
MMLU (cloze)	31.5
CommonsenseQA	33.9
OpenBookQA	34.6

⚙️ Base Model

Original author: HuggingFaceTB; SmolLM2 135M Instruct.

Warning: This repository may contain inaccurate, outdated, or otherwise unsuitable files. After fine-tuning, approximately half of the original files were left unchanged, so their contents may not reflect the current state of the project or may no longer be relevant.

📜 License

Apache 2.0 — you can use, modify, and share this code freely, even in commercial projects. The only requirement is to keep the original attribution. Full text in the file: LICENSE.