Costa Tsaousis

ktsaou's activity

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

liked a model 3 days ago

zai-org/GLM-5

Text Generation • 754B • Updated 9 days ago • 177k • • 1.41k

New activity in cerebras/MiniMax-M2.5-REAP-139B-A10B 3 days ago

nvfp4

➕ 👍 2

1

#1 opened 3 days ago by

ktsaou

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 4 days ago

accuracy

16

#4 opened 7 days ago by

ktsaou

liked a model 6 days ago

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

Text Generation • 32B • Updated 1 day ago • 1.08M • • 284

New activity in lukealonso/MiniMax-M2.5-NVFP4 7 days ago

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

👍 1

19

#2 opened 8 days ago by

zenmagnets

liked a model 8 days ago

MiniMaxAI/MiniMax-M2.5

Text Generation • Updated 6 days ago • 173k • • 841

New activity in mratsim/MiniMax-M2.1-FP8-INT4-AWQ 9 days ago

nvfp4

12

#9 opened 9 days ago by

festr2

liked a model 14 days ago

Qwen/Qwen3-Coder-Next

Text Generation • Updated 19 days ago • 415k • • 946

New activity in cerebras/MiniMax-M2.1-REAP-139B-A10B 21 days ago

4bit quant

#1 opened 21 days ago by

ktsaou

New activity in cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-4bit 21 days ago

extremely slow on vllm

#1 opened 21 days ago by

ktsaou

upvoted a collection about 1 month ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 28 items • Updated 3 days ago • 117

New activity in lukealonso/MiniMax-M2.1-NVFP4 about 1 month ago

This is perfect! Thank you!

🔥 1

14

#1 opened about 2 months ago by

ktsaou

New activity in MiniMaxAI/MiniMax-M2.1 about 2 months ago

NVFP4?

6

#2 opened about 2 months ago by

ktsaou

liked a model about 2 months ago

MiniMaxAI/MiniMax-M2

Text Generation • Updated Dec 23, 2025 • 509k • • 1.48k

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

MinimaxM2.1

3

#5 opened about 2 months ago by

reneho

liked a model about 2 months ago

MiniMaxAI/MiniMax-M2.1

Text Generation • Updated 9 days ago • 76.2k • • 1.26k

New activity in Firworks/Qwen3-Coder-REAP-25B-A3B-nvfp4 about 2 months ago

It works!

1

#1 opened about 2 months ago by

ktsaou

New activity in cerebras/Qwen3-Coder-REAP-25B-A3B about 2 months ago

NVFP4?

2

#9 opened about 2 months ago by

ktsaou

New activity in Firworks/Ministral-3-14B-Reasoning-2512-nvfp4 about 2 months ago

Gave it a try, here are my findings

#2 opened about 2 months ago by

ktsaou

New activity in RESMP-DEV/Qwen3-Next-80B-A3B-Instruct-NVFP4 about 2 months ago

Works with vllm? Any recommendations or howtos?

7

#1 opened 4 months ago by

DrRos