HelloSun

HelloSun's activity

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

New activity in LiquidAI/LFM3-1.7B 1 day ago

Community benchmark: LFM3-1.7B scores 93.6% on a 6-category sweep (Agent via Pi)

1

#13 opened 1 day ago by

HelloSun

New activity in HelloSun/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF_EPQ 11 days ago

程式碼級分析：為什麼 expert 全部放進 RAM（≥24 GiB）後，EPQ 仍比原生 llama.cpp 慢

3

#1 opened 11 days ago by

HelloSun

New activity in openbmb/MiniCPM5-1B-GGUF about 2 months ago

[Pi Coding Agent + Model] Integrated Evaluation -- FINAL CONSOLIDATED REPORT (English)

#8 opened about 2 months ago by

HelloSun

New activity in nvidia/NVIDIA-Nemotron-3-Nano-4B-GGUF 2 months ago

Model Evaluation – NVIDIA-Nemotron-3-Nano-4B-Q4_K_M.gguf (llama.cpp) on a Local Business Query

1

#2 opened 2 months ago by

HelloSun

New activity in poolside/Laguna-XS-2.1-GGUF 2 months ago

[Benchmark Report] Laguna-XS-2.1-Q4_K_M.gguf vs. Qwen3.6-35B-A3B-UD-Q4_K_M.gguf

#4 opened 2 months ago by

HelloSun

New activity in ornith-ai/Ornith-1.5-35B-A3B-GGUF 2 months ago

[llama.cpp CPU Benchmark] Qwen3.6-35B-MTP vs Ornith-1.5 – Pi Agent Evaluation

❤️ 2

1

#17 opened 2 months ago by

HelloSun

New activity in ornith-ai/Ornith-1.5-35B-A3B 2 months ago

[llama.cpp CPU Benchmark] Qwen3.6-35B-MTP vs Ornith-1.5 – Pi Agent Evaluation

#27 opened 2 months ago by

HelloSun

New activity in poolside/README 3 months ago

Is Laguna S 2.1 a fine-tune/distillation of Alibaba Cloud PAI / Qwen?

1

#1 opened 3 months ago by

HelloSun

New activity in tencent/Hy-MT2-7B-GGUF 4 months ago

本來希望蠻大 但是 測試結果顯然非常的不實用 錯誤百出 建議找該語言人士確認一下

#5 opened 4 months ago by

HelloSun

本來希望蠻大 但是 測試結果顯然非常的不實用 錯誤百出 建議找該語言人士確認一下

#5 opened 4 months ago by

HelloSun