Vision-Decision/Glance-COCO
Viewer • Updated • 88.2k • 38
Glance-X-Lite finds objects in an image from a text request, in English or Chinese. It answers with a box around every match, or says the object is not in the image. It is a 0.8B model with two directions:
| Direction | Cached | Best for |
|---|---|---|
image_first |
the image: encode once, then each request costs ~30 tokens | one image, many requests; a photo library searched again and again |
text_first |
the request; each new image reads it | one request over new images (camera, video); best multi-target recall |
Real outputs: one request over 256 cached images (68 ms on one GPU), then new requests inside the picked image.
The code is on GitHub: Vision-Decision/Glance-X-MLX.
pip install "glancex[fla] @ git+https://github.com/Vision-Decision/Glance-X-MLX" # drop [fla] without a CUDA GPU
from glancex import GlanceX
m = GlanceX.from_pretrained("Vision-Decision/Glance-X-Lite") # this repo + Qwen/Qwen3.5-0.8B-Base
m.ask("tennis.jpg", ["the kid with glasses in the middle", "左边举起球拍的男孩", "a frisbee"])
# Result('the kid with glasses in the middle', present_prob=1.000, box=[250, 153, 369, 422], confidence=0.991, n_boxes=1)
# Result('左边举起球拍的男孩', present_prob=0.983, box=[62, 146, 260, 427], confidence=0.979, n_boxes=1)
# Result('a frisbee', present_prob=0.000, box=[511, 134, 588, 261], confidence=0.000, n_boxes=0)
bank = m.encode(photos) # image cache, ~25 MB per image
m.search("a giraffe eating from someone's hand", bank)[0]
m.search("a giraffe eating from someone's hand", photos, mode="text_first")[0]
| File | Contents |
|---|---|
adapter_model.safetensors |
LoRA r=64 on every language-model linear layer of Qwen3.5-0.8B-Base (fp32, 164 MB) |
heads.safetensors |
presence, box (patch centre + 4×64-bin edges), IoU and multi-box objectness heads (25 MB) |
glancex_config.json |
model config (24 layers, K=2, positions, head sizes) |

image_first: the image is a shared prefix that never reads a request, so it can be cached.text_first: the request is the prefix, and the image tokens read it.Full splits, Acc@0.5 (%):
image_first |
text_first |
|
|---|---|---|
| RefCOCO val / testA / testB | 90.8 / 92.7 / 87.8 | 89.9 / 91.8 / 86.1 |
| RefCOCO+ val / testA / testB | 85.3 / 90.2 / 80.2 | 83.1 / 88.0 / 76.5 |
| RefCOCOg val / test | 87.5 / 87.7 | 85.9 / 85.5 |
| 8-split mean | 87.8 | 85.9 |
| gRefCOCO val: AUROC of P(present) / multi-target F1 | 97.4 / 75.0 | 96.4 / 76.1 |
| Glance-COCO: Acc@0.5 / multi-target F1 | 86.4 / 59.6 | 85.8 / 64.6 |
Latency on one H200, end to end (ms, N = 1 / 16 / 64 / 128):
| Workload | Latency |
|---|---|
| one image, N requests | 36 / 44 / 64 / 94 |
| one request, N cached images | 34 / 33 / 36 / 42 |
one request, N new images (text_first) |
38 / 181 / 658 / 1,293 |
For comparison, the 4B Glance-X2 scores 91.3 on the RefCOCO-family mean. Full tables are in RESULTS.md.
configs/lite/glance-x-lite.json.joint is not supported.Base model
Qwen/Qwen3.5-0.8B-Base