Instructions to use fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym with Transformers:

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

pipe = pipeline("text-generation", model="fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym")
model = AutoModelForCausalLM.from_pretrained("fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym

SGLang

How to use fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym 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 "fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym" \
    --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": "fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym",
		"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 "fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym" \
        --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": "fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym
```

Model Information

Quantized version of tiiuae/Falcon3-3B-Instruct using torch.bfloat16 for quantization tuning.

4 bits (INT4)
group size = 64
Symmetrical Quantization
Method: WoQ — GPTQ (AutoGPTQ algorithm)

Fast and low memory, 2-3X speedup (slight accuracy drop at W4G64)

Quantization framework: Intel AutoRound v0.13.1

Note: this INT4 version of Falcon3 3B Instruct has been quantized for inference on Intel CPU, Intel iGPU (Arc) via intel-extension-for-pytorch, Intel NPU (AI Boost on Core Ultra series) via OpenVINO.

Usage

This is an instruct / chat model — use its built-in chat template rather than raw text prompts:

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym"
model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(repo)

messages = [{"role": "user", "content": "Hello!"}]
inputs = tokenizer.apply_chat_template(
    messages, return_tensors="pt", add_generation_prompt=True
).to(model.device)
outputs = model.generate(inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Replication Recipe

The recommended way to reproduce this exact quantization is via the auto-round-pipeline — the same orchestration tool that produced this artifact.

Step 1 — Bootstrap the auto-round-pipeline

Set up a dedicated conda environment using the pipeline's setup.sh. Any of the install modes below produces an environment that can reproduce this quantization; pick the one that matches your goals:

git clone https://git.epicdynamic.com/auto-round-pipeline
cd auto-round-pipeline

# Pinned PyPI wheel (fastest; matches what this pipeline used by default):
bash setup.sh --pip-version 0.13.1

# Or build from intel/auto-round at the same tag (byte-identical reproducibility):
bash setup.sh --source-tag v0.13.1

# Intel Arc iGPU acceleration (e.g. Core Ultra 185H) — append to either of the above:
#   ... --intel-xpu
# NVIDIA / AMD opt-in: --cuda / --rocm

The script prints the resulting conda env name (something like auto-round-pipeline-v0.13.1[-src][-xpu|-cuda|-rocm]) at the end.

Step 2 — Quantize just this model

Activate the env that setup.sh created, then invoke the runner with the same job filters that produced this artifact:

conda activate <env-name-printed-by-setup.sh>
python runner.py \
    --model 'tiiuae/Falcon3-3B-Instruct' \
    --quant 'INT4-gs64' \
    --format auto_gptq \
    --no-upload      # drop this to also push to HuggingFace Hub

Step 3 — (Optional) standalone Python recipe

If you'd rather call auto-round directly without the orchestration wrapper, this is the exact call the pipeline made:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from auto_round import AutoRound

model_name = "tiiuae/Falcon3-3B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_name)

bits, group_size, sym = 4, 64, True
autoround = AutoRound(
    model, tokenizer,
    bits=bits, group_size=group_size, sym=sym,
    device_map="cpu",
    nsamples=128, iters=200, seqlen=512, batch_size=4,
)
autoround.quantize_and_save("./AutoRound/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym", format="auto_gptq")

Actual Run Conditions

Recorded by the auto-round-pipeline at quantization time:

Field	Value
Intel auto-round version	0.13.1
transformers version	4.55.3
torch version	2.12.1+cpu
torch_dtype (load)	torch.bfloat16
calibration device	`cpu`
calibration samples	128
tuning iterations	200
calibration seq len	512
calibration batch size	4
quantization duration	17471.4s (291.2 min)
completed at (UTC)	2026-07-05T20:13:24.268556+00:00

License

Apache 2.0 License

Disclaimer

This quantized model comes with no warranty. It has been developed only for research purposes.

Downloads last month: 12

Safetensors

Model size

1B params

Tensor type

F32

I32

Model tree for fbaldassarri/tiiuae_Falcon3-3B-Instruct-auto_gptq-int4-gs64-sym

Unable to build the model tree, the base model loops to the model itself. Learn more.