Instructions to use sKT-Ai-Labs/SPEED-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sKT-Ai-Labs/SPEED-1 with Transformers:

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

pipe = pipeline("text-generation", model="sKT-Ai-Labs/SPEED-1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("sKT-Ai-Labs/SPEED-1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("sKT-Ai-Labs/SPEED-1", trust_remote_code=True, device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sKT-Ai-Labs/SPEED-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sKT-Ai-Labs/SPEED-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sKT-Ai-Labs/SPEED-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sKT-Ai-Labs/SPEED-1

SGLang

How to use sKT-Ai-Labs/SPEED-1 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 "sKT-Ai-Labs/SPEED-1" \
    --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": "sKT-Ai-Labs/SPEED-1",
		"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 "sKT-Ai-Labs/SPEED-1" \
        --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": "sKT-Ai-Labs/SPEED-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sKT-Ai-Labs/SPEED-1 with Docker Model Runner:
```
docker model run hf.co/sKT-Ai-Labs/SPEED-1
```

SPEED 1

SKT AI LABS

SPEED-1 is a Mixture-of-Experts (MoE) language model with ~19B parameters, built by SKT AI LABS Private Limited, an Indian AI company based in Sidhi, Madhya Pradesh. It is designed for complex tasks across a wide range, trained for complex reasoning, with chain-of-thought data spanning agentic tasks, mathematics, and coding.

Evaluation Results

Early results from ongoing development (October 2026, evaluated on AMD MI300X). Detailed eval configuration will be published with the full release.

Benchmark	SPEED-1
Reasoning & Knowledge
HMMT (Feb 26)	49.0
HMMT (Nov 25)	45.0
MMMLU	56.0
MMLU-Pro	67.0
GPQA Diamond	56.0
Instruction Following & Agents
IFEval	64.8
IFBench	24.0

Reasoning

Reasoning (thinking traces) is supported via the chat template. Extended reasoning evaluations are pending the full release.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer (trust_remote_code needed for the custom class)
tokenizer = AutoTokenizer.from_pretrained("sKT-Ai-Labs/SPEED-1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    "sKT-Ai-Labs/SPEED-1",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

# Apply the model's chat template (SPEED uses ### User: / ### Assistant:)
messages = [{"role": "user", "content": "Create a Python CLI tool using docker-py that manages Docker containers. I need a watch command that listens to the Docker events stream and triggers a callback whenever a container dies with a non-zero exit code."}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True,
                                       return_tensors="pt").to("cuda") if torch.cuda.is_available() else \
          tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

# Generate (give it room to reason before it answers)
outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.6, top_p=0.9)
result = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(result)

Note: SPEED reasons inside tags before answering — keep max_new_tokens high (≥1024) or the reply is cut off mid-thought.

Citation

@misc{SPEED-1,
  author = {SKT AI LABS, India},
  title = {SPEED-1: Indic-first multilingual Mixture-of-Experts model},
  year = {2026},
  publisher = {SKT AI LABS},
  url = {https://huggingface.co/sKT-Ai-Labs/SPEED-1}
}

Downloads last month: 674

Safetensors

Model size

19B params

Tensor type

BF16

Model tree for sKT-Ai-Labs/SPEED-1

Finetunes

1 model

Collection including sKT-Ai-Labs/SPEED-1

SPEED-1

Collection

3 items • Updated about 16 hours ago