fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-auto_gptq-int8-gs64-asym
Model Information
Quantized version of meta-llama/Llama-3.2-3B-Instruct using torch.bfloat16 for quantization tuning.
- 8 bits (INT8)
- group size = 64
- Asymmetrical Quantization
- Method: WoQ — GPTQ (AutoGPTQ algorithm)
Quantization framework: Intel AutoRound v0.13.1
Note: this INT8 version of Llama 3.2 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/meta-llama_Llama-3.2-3B-Instruct-auto_gptq-int8-gs64-asym"
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 / --rocmThe 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 'meta-llama/Llama-3.2-3B-Instruct' \
--quant 'INT8-gs64' \
--format auto_gptq \
--no-upload # drop this to also push to HuggingFace HubStep 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 = "meta-llama/Llama-3.2-3B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_name)
bits, group_size, sym = 8, 64, False
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/meta-llama_Llama-3.2-3B-Instruct-auto_gptq-int8-gs64-asym", format="auto_gptq")Actual Run Conditions
Recorded by the auto-round-pipeline at quantization time:
License
Disclaimer
This quantized model comes with no warranty. It has been developed only for research purposes.