Idefics3-8B-Llama3
Hugging Face · HuggingFaceM4/Idefics3-8B-Llama3
Weights license: Apache 2.0 · code and components may use other terms
Quality
No comparable score
We track no public, comparable benchmark that covers this model yet. No score is inferred.
Reported by the publisher
Runs on
Fast memory holds it 90
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 90
Within memory, outside the fast part 26
Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.
Show all 26
One memory tier short 3
The same machines with the next memory size up would hold it in fast memory.
Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.
Hugging Face released Idefics3-8B-Llama3 on 2024-08-22: a vision-language model that answers about images, with 8.46B parameters on the Hugging Face count and the Apache 2.0 license. Languages the publisher declares: en.
License: commercial use allowed. At Q4 the weights load about 6.3 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.
Measured speed
No published measurement for this checkpoint
Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.
How to run
Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.
Library in source: transformers
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
import requests
import torch
from PIL import Image
from io import BytesIO
from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image
DEVICE = "cuda:0"
# Note that passing the image urls (instead of the actual pil images) to the processor is also possible
image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
image2 = load_image("https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg")
image3 = load_image("https://cdn.britannica.com/68/170868-050-8DDE8263/Golden-Gate-Bridge-San-Francisco.jpg")
processor = AutoProcessor.from_pretrained("HuggingFaceM4/Idefics3-8B-Llama3")
model = AutoModelForVision2Seq.from_pretrained(
"HuggingFaceM4/Idefics3-8B-Llama3", torch_dtype=torch.bfloat16
).to(DEVICE)
# Create inputs
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What do we see in this image?"},
]
},
{
"role": "assistant",
"content": [
{"type": "text", "text": "In this image, we can see the city of New York, and more specifically the Statue of Liberty."},
]
},
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "And how about this image?"},
]
},
]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
# Generate
generated_ids = model.generate(**inputs, max_new_tokens=500)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts)Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- HuggingFaceM4/Idefics3-8B-Llama3
- Task
- image-text-to-text
- Architecture
- Idefics3ForConditionalGeneration
- Library in source
- transformers
- Weight license
- Apache 2.0HuggingFaceM4/Idefics3-8B-Llama3 model card (Hugging Face) · read 2026-10-18source
- Commercial use
- Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
- Languages
- enModel card metadata · read 2026-10-25source
- Released
- Building and better understanding vision-language models: insights and future directions (Hugging Face, arXiv 2408.12637 v1) · read 2026-10-18source
Every stored field
- Revision checked
- fddb4ff79181e55a994674777e06cd5456ce3dc3
- Architecture
- Idefics3ForConditionalGeneration
- Library
- transformers
- Hub task tag
- image-text-to-text
- Formats
- transformers, safetensors
- Access
- Open download
- Publisher kind
- Official
- Hub parameter count
- 8,462,086,384safetensors.total
- Repository created
- 2024-08-05creation is not the model's release
- Repository updated
- 2024-12-02a commit is not a release date
- Hub downloads (30 days) · likes
- 55,044 · 307this repository only · read 2026-10-25
- Catalog state
- Hub config or weights found; no inventory benchmark link
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher model card
- License: HuggingFaceM4/Idefics3-8B-Llama3 model card (Hugging Face)
- Release date: Building and better understanding vision-language models: insights and future directions (Hugging Face, arXiv 2408.12637 v1)
Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.






























































