Oblx

OblxDev's activity

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

liked a Space 5 days ago

Running

1

Frontier Benchmark

🌍

1

Standardized benchmarks for evaluating LLM reasoning, knowle

New activity in zai-org/GLM-5.2 7 days ago

All my documents are deleted :(

🧠👍 4

10

#48 opened 16 days ago by

jbourny

New activity in Hikari07jp/Ternary-Bonsai-27B-Abliterated-LowDeg-GGUF 11 days ago

[WIP] IMHO it's...

#1 opened 11 days ago by

OblxDev

liked a model 11 days ago

Hikari07jp/Ternary-Bonsai-27B-Abliterated-LowDeg-GGUF

Text Generation • 27B • Updated 11 days ago • 7.85k • 21

liked 3 models 13 days ago

aoi-ot/VibeVoice-Large

Text-to-Speech • 9B • Updated Sep 25, 2025 • 2.87k • 236

black-forest-labs/FLUX.2-klein-9B

Image-to-Image • 9B • Updated Feb 24 • 331k • • 1.15k

Comfy-Org/z_image_turbo

Updated about 1 month ago • 5.22M • 795

New activity in zai-org/GLM-5.2 15 days ago

Anyone tried this to run only on standard PC ram only?

6

#46 opened 18 days ago by

gemstonebro

liked a model 15 days ago

JBrightmanAI/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED

9B • Updated 15 days ago • 31 • 1

upvoted a paper 16 days ago

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Paper • 2607.07769 • Published 25 days ago • 10

New activity in zai-org/GLM-5.2 18 days ago

Dense 60-120B model

👍👀 7

4

#31 opened about 1 month ago by

rtzurtz

New activity in zai-org/GLM-5 20 days ago

Is your model is using GEMINI?

2

#83 opened 20 days ago by

promaneh

New activity in zai-org/GLM-5.2 23 days ago

High Token Consumption and Cost Behavior in This Model

➕ 3

3

#33 opened about 1 month ago by

mehranpng

liked a model 23 days ago

nvidia/Kimi-K2.7-Code-DFlash

Text Generation • 3B • Updated 24 days ago • 2.23k • 12

liked a model 24 days ago

Jackrong/Qwopus3.5-27B-v3-GGUF

Image-Text-to-Text • 27B • Updated 24 days ago • 2.78k • 353

reacted to sergiopaniego's post with ❤️ 24 days ago

view post

Post

7724

Frontier models use distillation as a step of their post-training pipelines.

In 2026 it has three jobs: compress a big model into a small one, merge RL experts into a single model, and let a model teach itself.

I wrote up which frontier models use each one and how: https://huggingface.co/blog/sergiopaniego/distillation-2026

It pairs with Class 2 of the Training an Agent series Ben and I are doing, where we teach these techniques hands-on with TRL!

See translation

• 

• 
• 
• 
• 3 replies

·

👍

14

14

🔥

7

7

❤️

3

3

+

Reply

New activity in zai-org/CogVideoX-2b 24 days ago

aasddsd

1

#17 opened 24 days ago by

Amoo0206

New activity in zai-org/GLM-5.2 26 days ago

IDEA: Bitnet 1.58 (a4.8) version in future variants would be so incredible!

❤️ 6

4

#40 opened 26 days ago by

apiarium

liked a model about 1 month ago

yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2

Text Generation • 12B • Updated Jun 30 • 238k • 81

New activity in yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF about 1 month ago

He got bought out

🔥 8

5

#2 opened about 1 month ago by deleted