meta-llama
/

Llama-3.2-1B

Text Generation

text-generation-inference

Model card Files Files and versions

Instructions to use meta-llama/Llama-3.2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.2-1B with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.2-1B")

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

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use meta-llama/Llama-3.2-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-3.2-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.2-1B

How to use meta-llama/Llama-3.2-1B 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 "meta-llama/Llama-3.2-1B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "meta-llama/Llama-3.2-1B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.2-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use meta-llama/Llama-3.2-1B with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.2-1B
```

Resources

View closed (45)

Test PR from attacker

#383 opened 5 days ago by

Request to Reset Rejected Access Application for Llama 3.2 1B

#382 opened 5 days ago by

My request is rejected

#381 opened 15 days ago by

Access denied

#380 opened 15 days ago by

Request for Access

#379 opened 22 days ago by

access request for meta-llama/Llama-3.2-1B

#377 opened about 1 month ago by

Appeal for rejected access request to Llama 3.2 collection

#376 opened about 1 month ago by

Request for Manual Review / Reset of Rejected Llama 3.2 Access — Academic Research

#375 opened about 1 month ago by

Request for Access — Llama-3.2-1B

#374 opened about 1 month ago by

Request for Access Re-evaluation - Llama 3.2

#373 opened 2 months ago by

Hello Meta Llama Team

#372 opened 3 months ago by

Request to reset access request for Llama-3.2-1B

#371 opened 3 months ago by

Request: DOI

#369 opened 3 months ago by

Appeal for Reconsideration of Access Request to meta-llama/Llama-3.2-1B

#368 opened 3 months ago by

Request: DOI

#367 opened 4 months ago by

Can I please get the request approved?

#366 opened 4 months ago by

Access

#365 opened 4 months ago by

Appeal for Rejected Access Request - meta-llama/Llama-3.2-1B

#364 opened 4 months ago by

Access Request

#363 opened 4 months ago by

TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture

#362 opened 5 months ago by

Add EvalEval community eval results

#361 opened 5 months ago by

Request: DOI

#360 opened 5 months ago by

Access request rejected – could you please reset my request?

#359 opened 5 months ago by

Mine Gating Group Collection approvals on Hugging Face is still pending.

#358 opened 5 months ago by

Access request rejected – please reset

#357 opened 6 months ago by

Access Request

#356 opened 6 months ago by

[Apply for reset the access request which has been rejected]

#355 opened 6 months ago by deleted

Access Request

#354 opened 6 months ago by

Access Request

#352 opened 6 months ago by

Access Request

#351 opened 7 months ago by

Access request

#350 opened 7 months ago by

course-project

#348 opened 7 months ago by

Access-Request (National Taiwan University)

#347 opened 7 months ago by

fix: set `clean_up_tokenization_spaces` to `false`

#346 opened 7 months ago by

Access Request

#345 opened 7 months ago by

Access Request

#344 opened 7 months ago by

Access request

#343 opened 7 months ago by

Access Request

#341 opened 8 months ago by

Access Request

#340 opened 8 months ago by

testing

#339 opened 8 months ago by

Terminator-2026

Access Request

#338 opened 8 months ago by

limingwanggrant

Access request was rejected, accidentally not filling the "affiliate" section

#337 opened 8 months ago by

Access Application Re-review Request

#336 opened 8 months ago by

Access Rejection Reconsideration

#335 opened 8 months ago by

Discussion with empty pull_request parameter test

#333 opened 8 months ago by

Reject

#332 opened 9 months ago by

Request: DOI

#331 opened 9 months ago by

wanderingnomadd

Request Denied

#329 opened 10 months ago by

Reject

#328 opened 11 months ago by

Request access for llama3.2 models

#327 opened 11 months ago by