GiantAILab/YingMusic-Singer
Updated • 7
Javed Alam PRO
Javedalam
AI & ML interests
Ai user, tester, and developer of open source ai based applications.
Recent Activity
liked a model about 10 hours ago
GiantAILab/YingMusic-Singer liked a Space about 10 hours ago
hugging-apps/yingmusic-singer liked a model 3 days ago
Comfy-Org/MiniMax-Music-3Organizations
liked a
model about 10 hours ago
liked a
Space about 10 hours ago
liked 2
models 3 days ago
liked a
Space 4 days ago
A 3B Vision Model Running at 13 Tokens/Second — on a Phone
👍 1
2
#2 opened 4 days ago
by Javedalam
replied to their post 4 days ago
Based on the image, there is a person standing outdoors in front of a boat. The individual is wearing a brown hoodie with "GANDER MTN." written on it, blue jeans, and brown shoes. They are holding two large fish, one in each hand, by their mouths. The fish appear to be salmon, given their size and distinctive coloration. The background includes a boat on a trailer and some grassy areas.
replied to their post 4 days ago
The image shows a man standing outdoors with a group of people behind him. The background features colorful, striped mountains with hues of red, green, yellow, and purple. The sky is overcast with clouds, and there appears to be mist or low-hanging clouds around the mountain peaks. The man in the foreground is wearing a dark jacket over a gray T-shirt that has text and graphics on it, which include the words "Western Pennsylvania Mushroom Club." He has short, light-colored hair and is wearing glasses. The overall setting suggests a hiking or outdoor gathering in a scenic, possibly volcanic, landscape.
posted an update 4 days ago
Post
1947
A 3B Vision Model Running at 13 Tokens/Second — on a Phone
AI is moving from the cloud into your pocket.
I just tested Liquid AI's newly released LFM2.5-VL-3B locally on a Samsung Galaxy S26. The Q8_0 model ran through llama.cpp with Vulkan acceleration on the Qualcomm Adreno 840 GPU. I uploaded a real webpage screenshot from another device and asked the model to describe it.
It worked—and generated at 13.11 tokens per second.
That's significant for a 3B-class vision-language model running entirely on a phone. In my testing, LFM2.5-VL-3B is the most capable local vision model I've run on the S26 so far.
Liquid AI is building specifically for this world. Its focus is edge AI: capable models designed to run locally on phones, laptops, vehicles and other resource-constrained hardware instead of depending entirely on cloud inference. Its LFM family targets low memory usage, fast inference and deployment across CPUs, GPUs and NPUs.
LFM2.5-VL-3B brings vision into that strategy. It is an open-weight multimodal model capable of image understanding, OCR, document extraction, visual question answering and spatial reasoning. Liquid provides the weights publicly, including an official GGUF release for llama.cpp.
This is where open-weight AI gets interesting. A phone can now hold the model, process the image and generate useful multimodal responses locally at interactive speed.
No cloud GPU. No remote inference API. The phone is the AI computer.[LFM2.5-VL-3B — Hugging Face]( LiquidAI/LFM2.5-VL-3B)
[LFM2.5-VL-3B-GGUF — Hugging Face]( LiquidAI/LFM2.5-VL-3B-GGUF)
AI is moving from the cloud into your pocket.
I just tested Liquid AI's newly released LFM2.5-VL-3B locally on a Samsung Galaxy S26. The Q8_0 model ran through llama.cpp with Vulkan acceleration on the Qualcomm Adreno 840 GPU. I uploaded a real webpage screenshot from another device and asked the model to describe it.
It worked—and generated at 13.11 tokens per second.
That's significant for a 3B-class vision-language model running entirely on a phone. In my testing, LFM2.5-VL-3B is the most capable local vision model I've run on the S26 so far.
Liquid AI is building specifically for this world. Its focus is edge AI: capable models designed to run locally on phones, laptops, vehicles and other resource-constrained hardware instead of depending entirely on cloud inference. Its LFM family targets low memory usage, fast inference and deployment across CPUs, GPUs and NPUs.
LFM2.5-VL-3B brings vision into that strategy. It is an open-weight multimodal model capable of image understanding, OCR, document extraction, visual question answering and spatial reasoning. Liquid provides the weights publicly, including an official GGUF release for llama.cpp.
This is where open-weight AI gets interesting. A phone can now hold the model, process the image and generate useful multimodal responses locally at interactive speed.
No cloud GPU. No remote inference API. The phone is the AI computer.[LFM2.5-VL-3B — Hugging Face]( LiquidAI/LFM2.5-VL-3B)
[LFM2.5-VL-3B-GGUF — Hugging Face]( LiquidAI/LFM2.5-VL-3B-GGUF)
- 2 replies
liked a
model 6 days ago
published a
Space 11 days ago
updated a
Space 11 days ago
liked a
model 11 days ago
updated a
collection 15 days ago
liked a
Space 17 days ago
updated a
collection 17 days ago
liked a
Space 17 days ago
liked a
model 18 days ago
updated a
collection 18 days ago
liked a
model 18 days ago
