Luke Alonso

lukealonso's activity

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

updated a model 2 days ago

lukealonso/Qwen3.5-397B-A17B-NVFP4

Text Generation • Updated 1 day ago • 2.09k • 2

published a model 2 days ago

lukealonso/Qwen3.5-NVFP4

Updated 2 days ago • 54

liked a model 2 days ago

lukealonso/Qwen3.5-397B-A17B-NVFP4

Text Generation • Updated 1 day ago • 2.09k • 2

updated a model 2 days ago

lukealonso/MiniMax-M2.5-NVFP4

130B • Updated 2 days ago • 78.9k • 38

published a model 2 days ago

lukealonso/Qwen3.5-397B-A17B-NVFP4

Text Generation • Updated 1 day ago • 2.09k • 2

updated a model 17 days ago

lukealonso/MiniMax-M2.5-REAP-139B-A10B-NVFP4

80B • Updated 17 days ago • 14.1k • 25

New activity in lukealonso/MiniMax-M2.5-NVFP4 17 days ago

Request: NVFP4 version of MiniMax-M2.5-REAP-139B (to fit on a single RTX 6000 Pro)

14

#7 opened 22 days ago by

mondovero

New activity in lukealonso/GLM-5-NVFP4 18 days ago

Crash on first request on RTX Pro 6000 x8

👍 1

6

#3 opened 20 days ago by

koushd

New activity in cerebras/MiniMax-M2.5-REAP-139B-A10B 21 days ago

nvfp4

➕ 👍 2

1

#1 opened 22 days ago by

ktsaou

published a model 21 days ago

lukealonso/MiniMax-M2.5-REAP-139B-A10B-NVFP4

80B • Updated 17 days ago • 14.1k • 25

liked a model 23 days ago

vincentzed-hf/Qwen3.5-397B-A17B-NVFP4

Image-Text-to-Text • Updated 24 days ago • 21.5k • 11

New activity in lukealonso/MiniMax-M2.5-NVFP4 23 days ago

VLLM error for kv weight scaling - workaround

7

#6 opened 24 days ago by

ShaunEvansMD

fp8 kv cache

15

#4 opened 25 days ago by

festr2

updated a model 24 days ago

lukealonso/GLM-5-NVFP4

425B • Updated 24 days ago • 26.8k • 9

New activity in lukealonso/MiniMax-M2.5-NVFP4 24 days ago

Thanks for your effort

5

#5 opened 24 days ago by

darkstar3537

published a model 25 days ago

lukealonso/GLM-5-NVFP4

425B • Updated 24 days ago • 26.8k • 9

New activity in lukealonso/MiniMax-M2.5-NVFP4 25 days ago

KeyError: '110.w1.input_scale' with TRT

2

#3 opened 26 days ago by

guanwenyu1995

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

👍 1

20

#2 opened 27 days ago by

zenmagnets

New activity in lukealonso/MiniMax-M2.5-NVFP4 26 days ago

Here's the vLLM recipe I'm using with 2x RTX Pro 6000

👍 3

17

#1 opened 27 days ago by

zenmagnets

liked a model 27 days ago

lukealonso/MiniMax-M2.5-NVFP4

130B • Updated 2 days ago • 78.9k • 38