Costa Tsaousis

ktsaou's activity

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

upvoted a collection 17 days ago

Qwen3.5

Collection

21 items • Updated 6 days ago • 1.17k

liked a model 24 days ago

zai-org/GLM-5

Text Generation • 754B • Updated 1 day ago • 250k • • 1.8k

New activity in cerebras/MiniMax-M2.5-REAP-139B-A10B 24 days ago

nvfp4

➕ 👍 2

1

#1 opened 24 days ago by

ktsaou

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 25 days ago

accuracy

21

#4 opened 28 days ago by

ktsaou

liked a model 27 days ago

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8

Text Generation • 32B • Updated 22 days ago • 1.49M • • 304

New activity in lukealonso/MiniMax-M2.5-NVFP4 28 days ago

"w1_weight_scale_2 must match w3_weight_scale_2. Accuracy may be affected."

👍 1

20

#2 opened 29 days ago by

zenmagnets

liked a model 29 days ago

MiniMaxAI/MiniMax-M2.5

Text Generation • 229B • Updated 5 days ago • 506k • • 1.19k

New activity in mratsim/MiniMax-M2.1-FP8-INT4-AWQ 30 days ago

nvfp4

12

#9 opened about 1 month ago by

festr2

liked a model about 1 month ago

Qwen/Qwen3-Coder-Next

Text Generation • 80B • Updated Feb 3 • 1.15M • • 1.13k

New activity in cerebras/MiniMax-M2.1-REAP-139B-A10B about 1 month ago

4bit quant

#1 opened about 1 month ago by

ktsaou

New activity in cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-4bit about 1 month ago

extremely slow on vllm

#1 opened about 1 month ago by

ktsaou

upvoted a collection about 2 months ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated 18 days ago • 130

New activity in lukealonso/MiniMax-M2.1-NVFP4 2 months ago

This is perfect! Thank you!

🔥 1

14

#1 opened 3 months ago by

ktsaou

New activity in MiniMaxAI/MiniMax-M2.1 3 months ago

NVFP4?

6

#2 opened 3 months ago by

ktsaou

liked a model 3 months ago

MiniMaxAI/MiniMax-M2

Text Generation • 229B • Updated Dec 23, 2025 • 187k • • 1.49k

New activity in lukealonso/MiniMax-M2-NVFP4 3 months ago

MinimaxM2.1

3

#5 opened 3 months ago by

reneho

liked a model 3 months ago

MiniMaxAI/MiniMax-M2.1

Text Generation • 229B • Updated 30 days ago • 55.8k • • 1.27k

New activity in Firworks/Qwen3-Coder-REAP-25B-A3B-nvfp4 3 months ago

It works!

1

#1 opened 3 months ago by

ktsaou

New activity in cerebras/Qwen3-Coder-REAP-25B-A3B 3 months ago

NVFP4?

2

#9 opened 3 months ago by

ktsaou

New activity in Firworks/Ministral-3-14B-Reasoning-2512-nvfp4 3 months ago

Gave it a try, here are my findings

#2 opened 3 months ago by

ktsaou