Aaron Newsome

aaron-newsome's activity

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

New activity in nsparks/DeepSeek-V4-Flash-FP4-FP8-GGUF 2 days ago

Proposal for the Ultimate Local SOTA:

1

#2 opened 21 days ago by

netforcetech

New activity in unsloth/Kimi-K2.6-GGUF 6 days ago

512 GB + 24-44 Vram option

👍 1

1

#6 opened about 1 month ago by

DiegoVSulz

New activity in sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP about 1 month ago

FANTASTICAL and much appreciated!

#2 opened about 1 month ago by

aaron-newsome

New activity in xai-org/grok-2 about 1 month ago

Grok 3 release time?

➕ 2

5

#44 opened 5 months ago by

ZeroWw

New activity in lukealonso/MiniMax-M2.7-NVFP4 about 2 months ago

Thanks, thanks and more thanks. Many thanks.

15

#2 opened about 2 months ago by

aaron-newsome

Working configuration for Nvidia Blackwell

13

#4 opened about 2 months ago by

luismiguelsaez

New activity in unsloth/Qwen3.5-122B-A10B-GGUF 3 months ago

very fast!!!

❤️🤗 1

5

#2 opened 3 months ago by

rosspanda0

New activity in unsloth/Qwen3.5-397B-A17B-GGUF 3 months ago

Core dumped for me,

7

#3 opened 3 months ago by

aaron-newsome

How to enable vision encoder?

1

#10 opened 3 months ago by

stefan28123

Q3_K_XL works surprisingly fast for 3x3090 + 128 ram

🔥 8

7

#4 opened 3 months ago by

fizzacles

New activity in unsloth/MiniMax-M2.1-GGUF 4 months ago

Chat template issues with newer llama.cpp?

#9 opened 4 months ago by

aaron-newsome

New activity in stepfun-ai/Step-3.5-Flash 4 months ago

Question : Real-world use cases for Step-3.5-Flash

8

#24 opened 4 months ago by

Geodd

New activity in unsloth/MiniMax-M2.1-GGUF 4 months ago

Hot Damn This Model Cooks!

👍 6

12

#5 opened 5 months ago by

aaron-newsome

New activity in unsloth/GLM-4.7-Flash-GGUF 4 months ago

Jan 21: All GLM-4.7-Flash quants reuploaded - much better outputs!

🔥❤️ 7

29

#10 opened 4 months ago by

danielhanchen

New activity in zai-org/GLM-Image 4 months ago

This model is slow and ugly.

➕ 2

3

#14 opened 4 months ago by

sccssc

New activity in IQuestLab/IQuest-Coder-V1-40B-Instruct 5 months ago

IQuestLab is more like IFakeEvals...

🚀🔥 3

2

#5 opened 5 months ago by

coolpoodle

New activity in unsloth/GLM-4.7-GGUF 5 months ago

Never mind the benchmarks, MiniMax M2.1 outshines GLM 4.7

🤝 2

4

#11 opened 5 months ago by

aaron-newsome

New activity in unsloth/MiniMax-M2.1-GGUF 5 months ago

Report: getting 20 t/s with UD-Q4_K_XL and 72 VRAM

🔥 2

10

#2 opened 5 months ago by

SlavikF

New activity in unsloth/GLM-4.7-GGUF 5 months ago

UD-Q5_K_XL seemingly broken

6

#2 opened 5 months ago by

Nimbz

New activity in unsloth/Devstral-2-123B-Instruct-2512-GGUF 6 months ago

mmproj?

10

#1 opened 6 months ago by

aaron-newsome