Daniel Dias Rodrigues

nerun's activity

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

New activity in unsloth/gemma-4-E4B-it-qat-GGUF about 1 hour ago

Performance report on RX 6600 M

1

#9 opened 5 days ago by

nerun

New activity in cloudnathan5/gemma-4-12b-it-MTP-GGUF about 3 hours ago

Incredible, thank you

#1 opened about 3 hours ago by

nerun

New activity in unsloth/gemma-4-12B-it-qat-GGUF about 4 hours ago

MTP not working

1

#19 opened 3 days ago by

nerun

New activity in protoLabsAI/Ornith-1.5-9B-MTP-GGUF about 7 hours ago

Performance report with guide to help others

🤝🔥 1

#5 opened about 7 hours ago by

nerun

New activity in LiquidAI/LFM2.5-8B-A1B-GGUF 1 day ago

Q4 fails as an AI Agent, but Q5 rocks!

1

#8 opened 10 days ago by

nerun

New activity in unsloth/Qwen3.6-35B-A3B-MTP-GGUF 2 days ago

No Speed Increase on an MBP M3 Pro 36 GB

👍 3

2

#22 opened 4 months ago by

vbot

New activity in unsloth/gemma-4-12B-it-qat-GGUF 3 days ago

Will other quantizations be released?

#18 opened 3 days ago by

nerun

New activity in owao/Nanbeige4.2-3B-GGUF 8 days ago

Q4_K_M slower than Q8_0

3

#4 opened 8 days ago by

nerun

New activity in LiquidAI/LFM2.5-8B-A1B 8 days ago

Can't follow instructions

2

#8 opened 4 months ago by

pcomte

New activity in Nanbeige/Nanbeige4.2-3B 8 days ago

Q4_K_M slower than Q8_0

#35 opened 8 days ago by

nerun

New activity in LiquidAI/LFM2.5-8B-A1B-GGUF 11 days ago

`--conversation` is an invalid parameter for llama

#7 opened 11 days ago by

nerun

New activity in LiquidAI/LFM2.5-VL-3B-GGUF 12 days ago

Benchmark at RX 6600M

#3 opened 12 days ago by

nerun

New activity in ibm-granite/granite-4.2-8b-GGUF 12 days ago

As fast as Gemma 4 E4B (8B)

❤️ 1

1

#1 opened 12 days ago by

nerun

New activity in prism-ml/Bonsai-27B-gguf 16 days ago

Bonsai-27B Q1_0 less than 7 tk/s on llama.cpp b10612

8

#26 opened 24 days ago by

nerun

New activity in empero-ai/Qwen3.8-9B-Distill-GGUF 28 days ago

this is qwen 3.5, not 3.8

❤️ 1

6

#7 opened about 1 month ago by

Sranyi