9 4

Shawn Beltz

sbeltz

AI & ML interests

Agentic coding, surviving AGI, creating useful tools to get there.

Recent Activity

new activity 1 day ago

google/gemma-4-26B-A4B-it:QAT?

liked a model 15 days ago

zai-org/GLM-5.1

new activity 3 months ago

wbruna/TwinFlow-Z-Image-Turbo-sdcpp-GGUF:Conversions not working for me

View all activity

Organizations

None yet

New activity in google/gemma-4-26B-A4B-it 1 day ago

QAT?

#39 opened 1 day ago by

sbeltz

liked a model 15 days ago

zai-org/GLM-5.1

Text Generation • 754B • Updated 17 days ago • 286k • • 1.58k

New activity in wbruna/TwinFlow-Z-Image-Turbo-sdcpp-GGUF 3 months ago

Conversions not working for me

#1 opened 3 months ago by

sbeltz

New activity in unsloth/GLM-4.7-Flash-GGUF 3 months ago

Disable thinking?

#4 opened 3 months ago by

JankyMudFart

liked a model 3 months ago

wbruna/upscalers-sdcpp-gguf

16.7M • Updated Feb 28 • 484 • 9

New activity in upstage/Solar-Open-100B 4 months ago

Day 0 llama.cpp support?

👍❤️ 4

#3 opened 4 months ago by

sbeltz

New activity in bartowski/nvidia_Nemotron-3-Nano-30B-A3B-GGUF 5 months ago

Why is nothing smaller than Q4 quants?

#2 opened 5 months ago by

sbeltz

commented on New in llama.cpp: Model Management 5 months ago

Is there currently a way to have a "default" model if the request doesn't specify? Could be the currently loaded model or a specific model. (Just noticed one of my apps broke because it's used to llama-server not requiring a model name.)

commented on New in llama.cpp: Model Management 5 months ago

Awesome new feature! Can model selection be done on something other than requested model name? Like maybe specify the ranking in presets.ini, and then the highest ranked model that can satisfy the request will be the default. So maybe one model is best for short context, another (or the same with other settings) for when the context gets too long, and another when image input is required.