Instructions to use KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile with Transformers:

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

pipe = pipeline("text-generation", model="KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile")

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

tokenizer = AutoTokenizer.from_pretrained("KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile")
model = AutoModelForCausalLM.from_pretrained("KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile 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-1.5-250M-Instruct-Mobile:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile: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-1.5-250M-Instruct-Mobile:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile: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-1.5-250M-Instruct-Mobile:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile:Q4_K_M

Use Docker

docker model run hf.co/KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile"
# 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-1.5-250M-Instruct-Mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile:Q4_K_M

SGLang

How to use KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile 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-1.5-250M-Instruct-Mobile" \
    --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-1.5-250M-Instruct-Mobile",
		"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-1.5-250M-Instruct-Mobile" \
        --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-1.5-250M-Instruct-Mobile",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile with Ollama:
```
ollama run hf.co/KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile with Docker Model Runner:
```
docker model run hf.co/KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile:Q4_K_M
```

Lemonade

How to use KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile:Q4_K_M

Run and chat with the model

lemonade run user.KrynexAI-1.5-250M-Instruct-Mobile-Q4_K_M

List all available models

lemonade list

Atomic Chat

KrynexAI 1.5

KrynexAI 1.5 is the model that refers to the KrynexAI Main family. It has 250M params, 40B tokens trained on, with LLaMa arch.

⚙️ Config

Spec	Details
Parameters	250M
Tokens seen	~40.4B
Arch	Llama
Layers	32
Hidden size	768
Intermediate size (MLP)	1920
Attention heads	12 (head dim 64)
KV heads (GQA)	4
Vocabulary size	49,152
Context length	2,048
RoPE theta	10,000
Activation	SiLU (SwiGLU MLP)
Tied embeddings	Yes
Precision	bfloat16

💻 Hardware

This model was trained on a single A100 SXM.

Benchmarks

Benchmark	Shots	acc	acc_norm	Random
HellaSwag	0	31.64	37.18	25.0
PIQA	0	65.78	64.91	50.0
ARC-Easy	0	57.11	50.46	25.0
ARC-Challenge	0	25.00	26.28	25.0
Arithmark-v3	0	38.00	38.20	-
Open SLM leaderboard's II	-	20.64	-	-

🚀 How to use

This code should download the model and generate a response.

pip install transformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
checkpoint = "KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile"
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))

📜 License

This model is released under Apache-2.0 License — 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.