Sascha Afkhampour

trigger2k25's activity

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

updated a model about 10 hours ago

trigger2k25/Qwen3-Reranker-4B-oQ8e-bf16

Text Ranking • 4B • Updated about 10 hours ago • 8

published a model about 10 hours ago

trigger2k25/Qwen3-Reranker-4B-oQ8e-bf16

Text Ranking • 4B • Updated about 10 hours ago • 8

liked a model about 11 hours ago

sgrankin/Qwen3-Reranker-4B-oQ8-fp16

4B • Updated May 4 • 28 • 1

New activity in sgrankin/Qwen3-Reranker-4B-oQ8-fp16 about 11 hours ago

config.json declares bfloat16, but saved tensors are float16

#1 opened about 11 hours ago by

trigger2k25

New activity in incoai/Qwen3.8-27B-Splash about 1 month ago

Can we have a 8bit target ?

👍 1

1

#12 opened about 1 month ago by

trigger2k25

Testing on the M4 Max 128G. Yes, it’s faster than the alternatives, yet it still isn’t viable for regular work.

👀 1

2

#1 opened about 1 month ago by

szkane

updated a model about 2 months ago

trigger2k25/Qwen3.6-35B-A3B-oQ4e-fp16-mtp

36B • Updated Sep 11 • 20

published a model about 2 months ago

trigger2k25/Qwen3.6-35B-A3B-oQ4e-fp16-mtp

36B • Updated Sep 11 • 20

New activity in evsinlb/Qwen3.8-27B-oQ4e-mtp 2 months ago

evsinlb/Qwen3.8-27B-oQ8e-mtp

👍 1

1

#1 opened 2 months ago by

trigger2k25

published a model 2 months ago

trigger2k25/Qwen3.6-35B-A3B-heretic-BF16-mtp

Image-Text-to-Text • 36B • Updated Aug 24 • 101

updated a model 2 months ago

trigger2k25/Qwen3.6-35B-A3B-heretic-BF16-mtp

Image-Text-to-Text • 36B • Updated Aug 24 • 101