granite-vision-4.1-4b
IBM · ibm-granite/granite-vision-4.1-4b
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 118
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 118
Within memory, outside the fast part 1
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.
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.
IBM released granite-vision-4.1-4b on 2026-04-29: a vision-language model that answers about images, with 4B 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 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.
pip install torch==2.10.0 --index-url https://download.pytorch.org/whl/cu128
pip install transformers>=5.8.0 peft>=0.19.1 tokenizers>=0.22.2 pillow>=12.2.0import re
from io import StringIO
import pandas as pd
import torch
from transformers import AutoProcessor, AutoModelForImageTextToText
from PIL import Image
from huggingface_hub import hf_hub_download
model_id = "ibm-granite/granite-vision-4.1-4b"
device = "cuda" if torch.cuda.is_available() else "cpu"
processor = AutoProcessor.from_pretrained(model_id)
processor.tokenizer.padding_side = "left" # required for correct batched generation
model = AutoModelForImageTextToText.from_pretrained(
model_id,
dtype=torch.bfloat16,
device_map=device
).eval()
def run_inference(model, processor, images, prompts):
"""Run batched inference on image+prompt pairs (one image per prompt)."""
conversations = [
[{"role": "user", "content": [
{"type": "image"},
{"type": "text", "text": prompt},
]}]
for prompt in prompts
]
texts = [
processor.apply_chat_template(conv, tokenize=False, add_generation_prompt=True)
for conv in conversations
]
inputs = processor(
text=texts, images=images, return_tensors="pt", padding=True, do_pad=True
).to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=4096,
use_cache=True
)
results = []
for i in range(len(prompts)):
gen = outputs[i, inputs["input_ids"].shape[1]:]
results.append(processor.decode(gen, skip_special_tokens=True))
return results
def display_table(text):
"""Pretty-print CSV (possibly wrapped in ```csv```) or HTML table content via pandas."""
m = re.search(r"```csv\s*
(.*?)```", text, re.DOTALL)
if m:
df = pd.read_csv(StringIO(m.group(1)))
print(df.to_string(index=False))
elif "<table" in text.lower():
df = pd.read_html(StringIO(text))[0]
print(df.to_string(index=False))
else:
print(text)pip install vllm>=0.21.0vllm serve ibm-granite/granite-vision-4.1-4b --host 0.0.0.0 --port 8000pip install git+https://github.com/Blaizzy/mlx-vlm.gitmlx_vlm generate \
--model ibm-granite/granite-vision-4.1-4b \
--image chart.jpg \
--prompt "<chart2csv>"Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- ibm-granite/granite-vision-4.1-4b
- Task
- image-text-to-text
- Architecture
- Granite4VisionForConditionalGeneration
- Library in source
- transformers
- Weight license
- Apache 2.0ibm-granite/granite-vision-4.1-4b 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
- Granite-Vision-4.1-4B model card, 'Release Date: April 29th, 2026' (IBM, Hugging Face) · read 2026-10-18source
Every stored field
- Revision checked
- 37d591f06319e8f1638b5adcf58bdf50e0f84f7a
- Architecture
- Granite4VisionForConditionalGeneration
- Library
- transformers
- Hub task tag
- image-text-to-text
- Formats
- transformers, safetensors
- Access
- Open download
- Publisher kind
- Official
- Repository created
- 2026-04-16creation is not the model's release
- Repository updated
- 2026-07-13a commit is not a release date
- Hub downloads (30 days) · likes
- 123,417 · 112this 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: ibm-granite/granite-vision-4.1-4b model card (Hugging Face)
- Release date: Granite-Vision-4.1-4B model card, 'Release Date: April 29th, 2026' (IBM, Hugging Face)
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.






























































