Molmo-72B-0924
Ai2 · allenai/Molmo-72B-0924
Weights license: Apache 2.0 · code and components may use other terms
Quality
Quality · LMArena · vision
LMArena 2026-10-19 · human-preference rating · higher is better · this model outlined
- Color = publisher
Source: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0 · models without a rating are not drawn (no rating ≠ 0)
1,045 ± 13 · LMArena · vision · Confidence interval 1,032–1,058 · 3,048 votes
Reported by the publisher
Quality × memory
No comparable quality × memory pair
This entry has no score on a benchmark that is drawn against planning memory.
Ai2 released Molmo-72B-0924 on 2024-09-24: a vision-language model that answers about images, with 73.3B 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 55 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.
Runs on
Fast memory holds it 17
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 17
Within memory, outside the fast part 6
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.
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 einops torchvisionfrom transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
from PIL import Image
import requests
import torch
# load the processor
processor = AutoProcessor.from_pretrained(
'allenai/Molmo-72B-0924',
trust_remote_code=True,
torch_dtype='auto',
device_map='auto'
)
# load the model
model = AutoModelForCausalLM.from_pretrained(
'allenai/Molmo-72B-0924',
trust_remote_code=True,
torch_dtype='auto',
device_map='auto'
)
# process the image and text
inputs = processor.process(
images=[Image.open(requests.get("https://picsum.photos/id/237/536/354", stream=True).raw)],
text="Describe this image."
)
# move inputs to the correct device and make a batch of size 1
inputs = {k: v.to(model.device).unsqueeze(0) for k, v in inputs.items()}
# generate output; maximum 200 new tokens; stop generation when <|endoftext|> is generated
output = model.generate_from_batch(
inputs,
GenerationConfig(max_new_tokens=200, stop_strings="<|endoftext|>"),
tokenizer=processor.tokenizer
)
# only get generated tokens; decode them to text
generated_tokens = output[0,inputs['input_ids'].size(1):]
generated_text = processor.tokenizer.decode(generated_tokens, skip_special_tokens=True)
# print the generated text
print(generated_text)
# >>> This image features an adorable black Labrador puppy sitting on a wooden deck.
# The puppy is positioned in the center of the frame, looking up at the camera...Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- allenai/Molmo-72B-0924
- Task
- image-text-to-text
- Architecture
- MolmoForCausalLM
- Library in source
- transformers
- Weight license
- Apache 2.0allenai/Molmo-72B-0924 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
- Molmo README news, '2024/09/24 ... Molmo ... has been released' (allenai/molmo GitHub) · read 2026-10-18source
Every stored field
- Revision checked
- ab586dd9640de059566975b8e5bcd0c6fdc73956
- Architecture
- MolmoForCausalLM
- Library
- transformers
- Hub task tag
- image-text-to-text
- Declared base models
- openai/clip-vit-large-patch14-336 · Qwen/Qwen2-72B
- Formats
- transformers, safetensors
- Access
- Open download
- Publisher kind
- Official
- Hub parameter count
- 73,308,285,952safetensors.total
- Repository created
- 2024-09-25creation is not the model's release
- Repository updated
- 2025-10-09a commit is not a release date
- Hub downloads (30 days) · likes
- 7,952 · 300this 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: allenai/Molmo-72B-0924 model card (Hugging Face)
- Release date: Molmo README news, '2024/09/24 ... Molmo ... has been released' (allenai/molmo GitHub)
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.













