L

lovedheart's activity

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

updated a model 1 day ago

lovedheart/openPangu-2.0-Flash-GGUF-Preview

92B • Updated 1 day ago

published a model 1 day ago

lovedheart/openPangu-2.0-Flash-GGUF-Preview

92B • Updated 1 day ago

updated a model 3 days ago

lovedheart/openPangu-2.0-Flash-FP8

98B • Updated 3 days ago • 922

published a model 3 days ago

lovedheart/openPangu-2.0-Flash-FP8

98B • Updated 3 days ago • 922

upvoted a collection 8 days ago

Qwen3-ASR

Collection

7 items • Updated 8 days ago • 74

liked a model 8 days ago

Qwen/Qwen3-ASR-1.7B-hf

Automatic Speech Recognition • 2B • Updated 8 days ago • 6.96k • 28

New activity in lovedheart/Qwen-AgentWorld-35B-A3B-FP8 8 days ago

Share quant script

1

#2 opened 8 days ago by

verdverm

New activity in lovedheart/Qwen-AgentWorld-35B-A3B-FP8 9 days ago

You didn't quantize it, did you? FP8 can't be the same size as BF16.

1

#1 opened 10 days ago by

lsm03624

updated a model 9 days ago

lovedheart/Qwen-AgentWorld-35B-A3B-FP8

Text Generation • 35B • Updated 9 days ago • 10.4k

New activity in lovedheart/DeepSeek-V4-Flash-Lite-fastllm-Q2-Q3-Q4-Mixed 10 days ago

CPU only goes ERROR，Model may be not used

1

#2 opened 11 days ago by

Leeonne

updated a model 10 days ago

lovedheart/Qwen-AgentWorld-35B-A3B-NVFP4

Text Generation • 22B • Updated 10 days ago • 2.76k • 6

published 2 models 10 days ago

lovedheart/Qwen-AgentWorld-35B-A3B-NVFP4

Text Generation • 22B • Updated 10 days ago • 2.76k • 6

lovedheart/Qwen-AgentWorld-35B-A3B-FP8

Text Generation • 35B • Updated 9 days ago • 10.4k

liked a model 11 days ago

Qwen/Qwen-AgentWorld-35B-A3B

Text Generation • 35B • Updated 9 days ago • 50.2k • 531

upvoted a collection 11 days ago

Qwen-AgentWorld

Collection

3 items • Updated 10 days ago • 66

updated a model 17 days ago

lovedheart/Qwen3.6-27B-NVFP4-FP8-Mixed

Image-Text-to-Text • 20B • Updated 17 days ago • 49

published a model 17 days ago

lovedheart/Qwen3.6-27B-NVFP4-FP8-Mixed

Image-Text-to-Text • 20B • Updated 17 days ago • 49

updated a model 17 days ago

lovedheart/DeepSeek-V4-Flash-Lite-fastllm-Q2-Q3-Q4-Mixed

Text Generation • 149B • Updated 17 days ago • 38

published a model 17 days ago

lovedheart/DeepSeek-V4-Flash-Lite-fastllm-Q2-Q3-Q4-Mixed

Text Generation • 149B • Updated 17 days ago • 38

updated a model about 1 month ago

lovedheart/DeepSeek-V4-Flash-Lite

Text Generation • 121B • Updated May 27 • 348 • 3