Prithiv Sakthi PRO

prithivMLmods's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model about 1 hour ago

prithivMLmods/LFM2.5-350M-F32-GGUF

Text Generation • 0.4B • Updated about 1 hour ago • 1

published a model about 1 hour ago

prithivMLmods/LFM2.5-350M-F32-GGUF

Text Generation • 0.4B • Updated about 1 hour ago • 1

updated a model about 1 hour ago

prithivMLmods/LFM2.5-350M-F32-GGUF

Text Generation • 0.4B • Updated about 1 hour ago • 1

New activity in prithivMLmods/chandra-ocr-2-GGUF about 1 hour ago

Thank you for the Great model!

#3 opened 3 days ago by

vladimirxi

New activity in prithivMLmods/chandra-ocr-2-GGUF about 2 hours ago

not working with Ollama

5

#2 opened 5 days ago by

ahmgam

updated a model about 2 hours ago

prithivMLmods/chandra-ocr-2-GGUF

Image-Text-to-Text • 5B • Updated about 2 hours ago • 6.91k • 8

New activity in prithivMLmods/Qwen3.5-27B-abliterated-v2-MAX about 2 hours ago

Model useable for captioning ?

2

#1 opened about 2 hours ago by

Girzai

upvoted an article about 4 hours ago

view article

Article

Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents

• 

about 18 hours ago

•

26

upvoted a changelog about 16 hours ago

view changelog

Hugging Face Changelog

Storage Buckets for Spaces

about 19 hours ago

• 36

updated a Space about 18 hours ago

Running on Zero

MCP

46

SAM3 Demo

🏀

46

Unified foundation model for promptable segmentation

liked a model about 21 hours ago

prithivMLmods/Qwen3-VL-32B-Instruct-v2-MAX-MXFP4

Image-Text-to-Text • 19B • Updated about 21 hours ago • 1 • 2

published a model about 21 hours ago

prithivMLmods/Qwen3-VL-32B-Instruct-v2-MAX-MXFP4

Image-Text-to-Text • 19B • Updated about 21 hours ago • 1 • 2

upvoted a collection about 22 hours ago

v2-MAX [BF16 / NVFP4A16 / MXFP4A16/ FP8 Dynamic]

Collection

Version 2 in the Unredacted series, with much lower refusal limits, is available in different compression schemes. • 7 items • Updated 1 day ago • 2

updated a model 1 day ago

prithivMLmods/Qwen3-VL-32B-Instruct-v2-MAX-MXFP4

Image-Text-to-Text • 19B • Updated about 21 hours ago • 1 • 2

upvoted an article 1 day ago

view article

Article

Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device Optimizations

• 

27 days ago

•

14

updated a collection 1 day ago

v2-MAX [BF16 / NVFP4A16 / MXFP4A16/ FP8 Dynamic]

Collection

Version 2 in the Unredacted series, with much lower refusal limits, is available in different compression schemes. • 7 items • Updated 1 day ago • 2

upvoted a paper 1 day ago

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15, 2025 • 18

liked a model 1 day ago

prithivMLmods/Qwen3.5-27B-abliterated-v2-MAX-NVFP4

Image-Text-to-Text • 19B • Updated 1 day ago • 14 • 1

published a model 1 day ago

prithivMLmods/Qwen3.5-27B-abliterated-v2-MAX-NVFP4

Image-Text-to-Text • 19B • Updated 1 day ago • 14 • 1

updated a model 1 day ago

prithivMLmods/Qwen3.5-27B-abliterated-v2-MAX-NVFP4

Image-Text-to-Text • 19B • Updated 1 day ago • 14 • 1