Ljubomir Josifovski

ljupco's activity

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

upvoted a paper about 10 hours ago

RelayLLM: Efficient Reasoning via Collaborative Decoding

Paper • 2601.05167 • Published 2 days ago • 23

liked a dataset about 15 hours ago

mkurman/medical-SYNTH-reasoning-preview

Viewer • Updated about 16 hours ago • 1.85k • 42 • 1

liked a model 1 day ago

ai21labs/AI21-Jamba-Reasoning-3B

Text Generation • 3B • Updated Oct 8, 2025 • 4.95k • 128

upvoted a collection 1 day ago

Jamba Reasoning 3B

Collection

AI21's top-performing reasoning model that packs leading scores on intelligence benchmarks and highly-efficient processing into a compact 3B build • 2 items • Updated Oct 8, 2025 • 6

liked a model 1 day ago

ai21labs/AI21-Jamba2-3B

Text Generation • 3B • Updated 1 day ago • 182 • 25

liked 3 models 2 days ago

mlx-community/IQuest-Coder-V1-40B-Loop-Instruct-6bit

Text Generation • 40B • Updated 3 days ago • 99 • 1

mkurman/ConvGPT-0.2B-SYNTH-250B-EC

Text Generation • 0.2B • Updated 4 days ago • 11 • 4

abnormalmapstudio/Qwen3-Next-80B-A3B-Thinking-mxfp4-mlx

Text Generation • 80B • Updated Sep 15, 2025 • 135 • 4

upvoted a collection 3 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 21 items • Updated about 13 hours ago • 80

liked 2 models 3 days ago

cerebras/Kimi-Linear-REAP-35B-A3B-Instruct

Text Generation • 35B • Updated Nov 6, 2025 • 942 • 59

ServiceNow-AI/Apriel-1.6-15b-Thinker

Image-Text-to-Text • 15B • Updated 19 days ago • 8.71k • • 255

upvoted a paper 3 days ago

Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits

Paper • 2512.20578 • Published 18 days ago • 68

upvoted a collection 4 days ago

DFlash

Collection

Block Diffusion for Flash Speculative Decoding • 2 items • Updated 5 days ago • 9

upvoted a collection 5 days ago

Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 67 items • Updated 10 days ago • 296

upvoted an article 5 days ago

view article

Article

M2.1: Multilingual and Multi-Task Coding with Strong Generalization

• 

5 days ago

•

27

liked a model 5 days ago

miromind-ai/MiroThinker-v1.5-235B

Text Generation • 235B • Updated 4 days ago • 1.07k • 192

upvoted a collection 5 days ago

MiroThinker-v1.5

Collection

MiroMind’s Flagship Search Agent Model • 4 items • Updated 3 days ago • 19

liked a model 5 days ago

0xSero/MiniMax-M2.1-REAP-25

Text Generation • 173B • Updated 6 days ago • 158 • 9

liked a model 6 days ago

0xSero/MiniMax-M2.1-REAP-50-W4A16

Text Generation • 17B • Updated 6 days ago • 1.89k • 26

upvoted a collection 6 days ago

Youtu

Collection

4 items • Updated 4 days ago • 10