Apriel-1.6-15b-Thinker
ServiceNow · ServiceNow-AI/Apriel-1.6-15b-Thinker
Weights license: MIT · 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
- Average Score
- 53.62
- BFCL v3 only
- 63.50Function Calling
- Tau2 bench Telecom
- 69Function Calling
- Tau2 bench Retail
- 66.67Function Calling
- Tau2 bench Airline
- 58Function Calling
- ComplexFuncBench
- 33.2Function Calling
- Agent IF
- 57.2Instruction Following
- Multi IF
- 83.34Instruction Following
Every reported result
- Multi-Challenge
- 46.15Instruction Following
- IF Bench
- 69Instruction Following
- AIME 25
- 88Math
- Struct Eval
- 79Coding
- LCB
- 81Coding
- SciCode
- 37Coding
- DeepresearchBench
- 36.47Agentic
- GAIA
- 40Agentic
- Work-Arena L1
- 59.1Agentic
- OS World Small
- 16.70Agentic
- SWE Bench Verified
- 23Agentic
- Terminal Bench
- 14Agentic
- Aider Polyglot
- 37.68Agentic
- MMLU Pro
- 79Knowledge
- Creative writing v3 / EQ Bench
- 59.73Creative Writing
- GPQA Diamond
- 73Others
- HLE
- 10Others
- AA LCR
- 50Long Context
- MMMU (validation)
- 72VLMEvalKit
- MMMU-PRO (10 choice)
- 60.28VLMEvalKit
- MMMU-PRO (Vision Only)
- 52.89VLMEvalKit
- LogicVista
- 58.61VLMEvalKit
- MathVision
- 60.85VLMEvalKit
- MathVista
- 79.90VLMEvalKit
- MathVerse (Vision Dominant)
- 66.75VLMEvalKit
- MathVerse (Text Dominant)
- 79.06VLMEvalKit
- MMStar
- 70.66VLMEvalKit
- CharXiv (descriptive)
- 89.85VLMEvalKit
- CharXiv (reasoning)
- 56.00VLMEvalKit
- AI2D Test
- 86.04VLMEvalKit
- BLINK
- 63.96VLMEvalKit
Values as printed on the card, with the publisher's own settings (card section: Evaluation); column “Apriel-1.6-15B-Thinker”. Not comparable across publishers and not used in any ranking. Model card
Runs on
Fast memory holds it 82
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 82
Within memory, outside the fast part 34
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 34
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.
ServiceNow released Apriel-1.6-15b-Thinker on 2025-12-09: a vision-language model that answers about images, with 14.9B parameters on the Hugging Face count and the MIT license.
License: commercial use allowed. At Q4 the weights load about 11.1 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 transformers# Tested with transformers==4.48
import re
import requests
import torch
from PIL import Image
from transformers import AutoProcessor, AutoModelForImageTextToText
# Load model
model_id = "ServiceNow-AI/Apriel-1.6-15b-Thinker"
model = AutoModelForImageTextToText.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
processor = AutoProcessor.from_pretrained(model_id)
# Example 1: Text-only prompt
chat = [
{
"role": "user",
"content": [
{"type": "text", "text": "What is the capital for France?"},
],
}
]
inputs = processor.apply_chat_template(chat, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt")
inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
inputs.pop("token_type_ids", None)
with torch.no_grad():
output_ids = model.generate(**inputs, max_new_tokens=1024, do_sample=True, temperature=0.6)
generated_ids = output_ids[:, inputs['input_ids'].shape[1]:]
output = processor.decode(generated_ids[0], skip_special_tokens=True)
response = re.findall(r"\[BEGIN FINAL RESPONSE\](.*?)(?:<\|end\|>)", output, re.DOTALL)[0].strip()
print("Text-only Response:", response)
# Example 2: Image understanding
url = "https://picsum.photos/id/237/200/300"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
chat = [
{
"role": "user",
"content": [
{"type": "text", "text": "Which animal is this?"},
{"type": "image"},
],
}
]
prompt = processor.apply_chat_template(chat, add_generation_prompt=True, tokenize=False)
inputs = processor(text=prompt, images=[image], return_tensors="pt").to(model.device)
with torch.no_grad():
output_ids = model.generate(**inputs, max_new_tokens=1024, do_sample=True, temperature=0.6)
generated_ids = output_ids[:, inputs['input_ids'].shape[1]:]
output = processor.decode(generated_ids[0], skip_special_tokens=True)
response = re.findall(r"\[BEGIN FINAL RESPONSE\](.*?)(?:<\|end\|>)", output, re.DOTALL)[0].strip()
print("Image Response:", response)
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- ServiceNow-AI/Apriel-1.6-15b-Thinker
- Task
- image-text-to-text
- Architecture
- LlavaForConditionalGeneration
- Library in source
- transformers
- Weight license
- MITServiceNow-AI/Apriel-1.6-15b-Thinker model card (Hugging Face front matter: license mit) · read 2026-10-19source
- Commercial use
- Allowed MIT license text (SPDX) · read 2026-10-18license text
- Released
- Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance (Hugging Face blog post by the publisher; JSON-LD datePublished) · read 2026-10-19secondary source
Every stored field
- Revision checked
- 5810d5f1723032300131e677450d7f95a15a05e7
- Architecture
- LlavaForConditionalGeneration
- Library
- transformers
- Hub task tag
- image-text-to-text
- Formats
- transformers, safetensors
- Access
- Open download
- Publisher kind
- Official
- Hub parameter count
- 14,863,859,712safetensors.total
- Repository created
- 2025-11-28creation is not the model's release
- Repository updated
- 2025-12-22a commit is not a release date
- Hub downloads (30 days) · likes
- 1,335 · 308this 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: ServiceNow-AI/Apriel-1.6-15b-Thinker model card (Hugging Face front matter: license mit)
- Release date: Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance (Hugging Face blog post by the publisher; JSON-LD datePublished) (secondary source)
Curated facts checked: 2026-10-19. 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.






























































