AxionLab

AxionLab-official's activity

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

liked a Space 1 day ago

Running

Agents

9

SLM Bistro

🥐

9

Run & Train Small LMs Easy & Free w/ GGUF, PEFT & more!

reacted to Banaxi-Tech's post with 😔 3 days ago

view post

Post

5,556

BananaMind 3 is going to be an comeback. Sorry for the BGA things ( i genuinely didnt know about nsa existing and yes I used aiiii)
Were going to use our BananaMind 2.1 Unified architecture with some changes + NSA and some other stuff.

See translation

• 
• 
• 
• 40 replies

·

👍

4

4

🔥

2

2

🚀

2

2

😔

2

2

👀

2

2

+

Reply

New activity in SupraLabs/Supra2-100M-Instruct 3 days ago

Supra2-100M-Instruct on black-router

1

#5 opened 12 days ago by

shimbaaa

liked a model 3 days ago

liodon-ai/Supra2-100M-Instruct-imatrix-GGUF

Text Generation • 0.1B • Updated Aug 7 • 424 • 5

New activity in AxiomicLabs/Open_SLM_Leaderboard 4 days ago

Public Execution Policy

9

#264 opened 4 days ago by

spitfire4794

reacted to Banaxi-Tech's post with 😔 5 days ago

view post

Post

4,875

BananaMind is in the google situation before argon right now, right?

See translation

• 
• 
• 
• 29 replies

·

😔

10

10

👍

6

6

🧠

2

2

+

Reply

liked a model 5 days ago

AxionLab-official/DogeAI-v1.0-Instruct-DISCONTINUED

Text Generation • Updated Mar 10 • 13 • 1

reacted to appvoid's post with 🔥 5 days ago

view post

Post

3,937

You know, I can't believe we are actually doing it, literally advancing the frontier at the edge! We've come a long way since the first models on open slm leaderboard, and, as many things that change, performance is one of the main things that has exploded.

7 years ago, the best we had was GPT-2. Today, we got 90m models beating smollm2! I can't barely see what a future with increasingly powerful small models will look like.

All I can say is that the best is yet to come. And will be agentic.

See translation

• 
• 
• 
• 11 replies

·

🔥

12

12

🚀

1

1

+

Reply

liked 2 Spaces 5 days ago

Running on Zero

Agents

4

Tiny T2I Arena

💻

4

Compare AI-generated images and rank models

Running on Zero

MCP

4

Image-Upscaler-1M

🔍

4

Tiny 885K-param super-resolution upscaler with hop chains

liked 2 datasets 6 days ago

Zyphra/Zyda-2

Preview • Updated Aug 6, 2025 • 41.9k • 105

nvidia/OpenMathInstruct-2

Viewer • Updated Nov 25, 2024 • 22M • 105k • 270

upvoted a collection 6 days ago

Supra2.5

Collection

Supra2.5: Latest state-of-the-art flagship model family releases • 1 item • Updated 7 days ago • 5

liked 2 models 6 days ago

Glint-Research/Image-Upscaler-1M

Updated about 1 month ago • 155 • 7

SupraLabs/Supra2.5-Pico

Text Generation • 2.98M • Updated 7 days ago • 294 • 16

liked a model 7 days ago

MinimaLabs/KLM-1.5

Text Generation • 99M • Updated 7 days ago • 490 • 25

upvoted an article 7 days ago

view article

Article

When Benchmark Numbers Become Marketing

• 

DedeProGames

•

Sep 17

• 12

liked a model 7 days ago

arthurblg1802/The-Giant

26959.9T • Updated 7 days ago • 184 • 1

liked a dataset 8 days ago

mistralai/gsm8k_speech

Viewer • Updated Jul 15, 2025 • 1.32k • 387 • 12

reacted to their post with 🚀 10 days ago

view post

Post

3,765

Tommorow we are releasing Supra2-Pro(100M params), our flagship, get ready!

(follow SupraLabs to get tuned in!)

SupraLabs

See translation

• 
• 
• 
• 9 replies

·

🔥

16

16

🚀

8

8

+

Reply