Agash Thamo

agash-thamo

·

Agash

AI & ML interests

None yet

Recent Activity

reacted to mike-ravkine's post with 🔥 17 days ago

I went into this expecting to find a ~Q2 garbage dumpster but https://huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf is a slick feat of QAT engineering. It is weaker then FP16 on a handful of tasks where quants usually degrade, as per their own paper the loss is "concentrated on sustained chains of reasoning / agentic" and in ReasonScape this bites on Sort, Shuffle and Dates, but counter-acting this are some noticeable improvements to thinking length without accuracy loss on several other tasks (Shapes, Cars). I haven't had a chance to run the Binary yet, but PQ2 + Bonsai QAT are confirmed to be pretty darn impressive.

liked a model 18 days ago

microsoft/SchGen

liked a model 19 days ago

Flix-AI/flix-swissgerman-full

View all activity

Organizations

None yet

liked a model 18 days ago

microsoft/SchGen

Updated Jun 8 • 153 • 25

liked a model 19 days ago

Flix-AI/flix-swissgerman-full

Automatic Speech Recognition • 2B • Updated Jun 12 • 2.1k • 6

liked 2 models 20 days ago

MuScriptor/muscriptor-large

1B • Updated Jul 10 • 3.74k • 133

OpenMOSS-Team/MOSS-Transcribe-Diarize

Audio-Text-to-Text • 0.9B • Updated 11 days ago • 194k • 374

liked a model 23 days ago

Jeyaram-K/piper-tamil-voices

Text-to-Speech • Updated 21 days ago • 4

liked a model 25 days ago

efficiencyx/Jun-Lora-v2-GGUF

Text Generation • 12B • Updated Jun 26 • 218 • 4

liked a model about 1 month ago

bosonai/higgs-tts-3-4b

Text-to-Speech • 5B • Updated Jul 9 • 290k • 708

liked a model about 2 months ago

sapientinc/HRM-Text-1B

Text Generation • 1B • Updated May 21 • 26.6k • 807

liked 2 models 9 months ago

OpenMotionLab/motiongpt3

Updated Oct 27, 2025 • 10

ReadyArt/Dark-Desires-12B-v1.5-GGUF

12B • Updated Oct 28, 2025 • 267 • 15

liked a model 10 months ago

google/medgemma-27b-it

Image-Text-to-Text • 29B • Updated Jul 10, 2025 • 92.9k • 404

liked a model 11 months ago

Wan-AI/Wan2.2-Animate-14B

Video-to-Video • 17B • Updated Nov 5, 2025 • 19.7k • 1.24k

liked 4 models 12 months ago

openbmb/MiniCPM-V-4_5

Image-Text-to-Text • 9B • Updated Mar 10 • 470k • 1.1k

Qwen/Qwen2.5-Omni-7B

Any-to-Any • 11B • Updated Apr 30, 2025 • 319k • 1.92k

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Jan 22 • 89.4k • 2.45k

Phr00t/WAN2.2-14B-Rapid-AllInOne

Image-to-Video • Updated Apr 6 • 1.64k

liked 3 models over 1 year ago

NexaAI/OmniAudio-2.6B

Audio-Text-to-Text • 0.6B • Updated Dec 13, 2024 • 312 • 289

convaitech/NEUROSYNC

Updated Jul 20, 2025 • 5 • 70

mistralai/Pixtral-12B-2409

Updated Jun 2 • 7.71k • 693

liked a model about 2 years ago

Sao10K/L3-8B-Stheno-v3.2

Text Generation • 8B • Updated Jun 7, 2024 • 5k • • 433