NghiemAbe/ViWikiFC
Viewer • Updated • 20.9k • 15 • 3
👋 Open to Work
Duy Nguyen
1plus1
Phcogdai's profile picture
webbrain-one-905954's profile picture
webbrain-one-612959's profile picture·
AI & ML interests
Computer Vision • Generative AI • RAG • Multimodal AI
Recent Activity
new activity about 12 hours ago
NghiemAbe/ViWikiFC:Dataset access liked a dataset about 12 hours ago
NghiemAbe/ViWikiFC liked a model 3 days ago
nvidia/Nemotron-3-Embed-8B-BF16Organizations
None yet
Dataset access
#2 opened about 12 hours ago
by 1plus1
liked a
dataset about 12 hours ago
liked 6
models 3 days ago
nvidia/Nemotron-3-Embed-8B-BF16
Sentence Similarity • 8B • Updated • 135k • 113
nvidia/Nemotron-3-Embed-1B-BF16
Sentence Similarity • 1B • Updated • 309k • • 173
nvidia/Nemotron-3.5-Embed-8B-BF16
Visual Document Retrieval • 8B • Updated • 5.81k • 34
nvidia/Nemotron-3.5-Embed-1B-BF16
Visual Document Retrieval • 2B • Updated • 15k • 58
Qwen/Qwen3.8-Flash-Next-FP8
Image-Text-to-Text • 180B • Updated • 146k • • 291
Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 7.92M • • 19k
reacted to alphabell-research's post with 👍 5 days ago
Post
2,999
One number missing from LFM3's on-device story: memory at 256K context. Liquid AI reports 1.90 GB peak on iPhone 17 Pro at 32K. From the pinned config, f16 K/V cache alone would be 0.41 GB at 32K, 1.61 GB at 128K and 3.22 GB at 256K, before weights and runtime buffers. The chart shows the calculation, not a phone measurement. If you have run longer contexts on-device, share peak memory and time to first token here: LiquidAI/LFM3-1.7B#5
Model: LiquidAI/LFM3-1.7B
Model: LiquidAI/LFM3-1.7B
- 3 replies
upvoted a paper 3 months ago
Missing dataset metadata/information
1
#2 opened 5 months ago
by 1plus1
liked a
Space 7 months ago
liked a
dataset 7 months ago
updated a
Space 7 months ago
published a
Space 7 months ago
updated a
Space 7 months ago
liked 2
Spaces 7 months ago
updated a
Space 7 months ago
published a
Space 7 months ago