Keye-VL-1_5-8B
Kwai Keye · Kwai-Keye/Keye-VL-1_5-8B
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.
Kwai Keye released Keye-VL-1_5-8B on 2025-08-28: a vision-language model for video and images, with 8.7B 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 6.5 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 --upgrade keye-vl-utils==1.5.2 -i https://pypi.org/simplefrom transformers import AutoModel, AutoTokenizer, AutoProcessor
from keye_vl_utils import process_vision_info
# default: Load the model on the available device(s)
model_path = "Kwai-Keye/Keye-VL-1_5-8B"
model = AutoModel.from_pretrained(
model_path,
torch_dtype="auto",
trust_remote_code=True,
# flash_attention_2 is recommended for better performance
attn_implementation="flash_attention_2",
).eval()
model.to("cuda")
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
# Image Inputs
## Non-Thinking Mode
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"image": "https://s1-11508.kwimgs.com/kos/nlav11508/mllm_all/ziran_jiafeimao_11.jpg",
},
{"type": "text", "text": "Describe this image./no_think"},
],
}
]
## Auto-Thinking Mode
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"image": "https://s1-11508.kwimgs.com/kos/nlav11508/mllm_all/ziran_jiafeimao_11.jpg",
},
{"type": "text", "text": "Describe this image."},
],
}
]
## Thinking mode
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"image": "https://s1-11508.kwimgs.com/kos/nlav11508/mllm_all/ziran_jiafeimao_11.jpg",
},
{"type": "text", "text": "Describe this image./think"},
],
}
]
# The default range for the number of visual tokens per image in the model is 4-20480.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 32-1280, to balance performance and cost.
# min_pixels = 32 * 28 * 28
# max_pixels = 1280 * 28 * 28
# e.g.,
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"image": "https://s1-11508.kwimgs.com/kos/nlav11508/mllm_all/ziran_jiafeimao_11.jpg",
"min_pixels": 32 * 28 * 28,
"max_pixels": 1280 * 28 * 28
},
{"type": "text", "text": "Describe this image./think"},
],
}
]
# Video inputs
messages = [
{
"role": "user",
"content": [
{
"type": "video",
"video": "http://s2-11508.kwimgs.com/kos/nlav11508/MLLM/videos_caption/98312843263.mp4",
},
{"type": "text", "text": "Describe this video."},
],
}
]
# You can also set fps and max_frames to restrict total frames send to model.
# e.g.,
messages = [
{
"role": "user",
"content": [
{
"type": "video",
"video": "http://s2-11508.kwimgs.com/kos/nlav11508/MLLM/videos_caption/98312843263.mp4",
"fps": 2.0,
"max_frames": 1024
},
{"type": "text", "text": "Describe this video."},
],
}
]
# Text inputs
messages = [
{
"role": "user",
"content": "Hello, Keye",
}
]
# Preparation for inference
text = processor.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs, mm_processor_kwargs = process_vision_info(messages)
inputs = processor(
text=[text],
images=image_inputs,
videos=video_inputs,
padding=True,
return_tensors="pt",
**mm_processor_kwargs
)
inputs = inputs.to("cuda")
# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=1024)
generated_ids_trimmed = [
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)pip install keye-vl-utils==1.5.2 "vllm>=0.9.2"vllm serve \
Kwai-Keye/Keye-VL-1_5-8B \
--tensor-parallel-size 8 \
--enable-prefix-caching \
--gpu-memory-utilization 0.8 \
--host 0.0.0.0 \
--port 8000 \
--trust-remote-codeTechnical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- Kwai-Keye/Keye-VL-1_5-8B
- Task
- video-text-to-text
- Architecture
- KeyeVL1_5ForConditionalGeneration
- Library in source
- transformers
- Weight license
- Apache 2.0Kwai-Keye/Keye-VL-1_5-8B 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
- Keye-VL-1.5 model card news: "2025.08.28 ... introduce Kwai Keye-VL-1.5" (Hugging Face) · read 2026-10-18source
Every stored field
- Revision checked
- b4d413e4f42a3999af1f5ba0e281c7d51d6b93de
- Architecture
- KeyeVL1_5ForConditionalGeneration
- Library
- transformers
- Hub task tag
- video-text-to-text
- Formats
- transformers, safetensors
- Access
- Open download
- Publisher kind
- Official
- Hub parameter count
- 8,696,835,648safetensors.total
- Repository created
- 2025-08-26creation is not the model's release
- Repository updated
- 2026-02-05a commit is not a release date
- Hub downloads (30 days) · likes
- 11,400 · 71this 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: Kwai-Keye/Keye-VL-1_5-8B model card (Hugging Face)
- Release date: Keye-VL-1.5 model card news: "2025.08.28 ... introduce Kwai Keye-VL-1.5" (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.






























































