John Leimgruber III PRO

ubergarm's activity

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

New activity in sszymczyk/DeepSeek-V3.2-nolight-GGUF about 17 hours ago

Feedback

17

#1 opened 6 days ago by

bibproj

New activity in ubergarm/DeepSeek-V3.2-Speciale-GGUF 2 days ago

Testing IQ5_K

🤗 1

2

#2 opened 2 days ago by

shewin

updated a model 3 days ago

ubergarm/DeepSeek-V3.2-Speciale-GGUF

Text Generation • 671B • Updated 3 days ago • 920 • 5

New activity in ubergarm/DeepSeek-V3.2-Speciale-GGUF 3 days ago

Say Whattt?!

🔥 👍 3

3

#1 opened 3 days ago by

mtcl

published a model 3 days ago

ubergarm/DeepSeek-V3.2-Speciale-GGUF

Text Generation • 671B • Updated 3 days ago • 920 • 5

liked a model 4 days ago

deepseek-ai/DeepSeek-V3.2-Speciale

Text Generation • 685B • Updated Dec 1, 2025 • 26.9k • 638

New activity in deepseek-ai/DeepSeek-V3.2-Speciale 4 days ago

GGUF quants?

2

#17 opened 14 days ago by

fsaudm

liked a model 4 days ago

sszymczyk/DeepSeek-V3.2-nolight-GGUF

671B • Updated 4 days ago • 414 • 9

New activity in ubergarm/GLM-4.7-GGUF 5 days ago

Is this a thinking model?

3

#10 opened 6 days ago by

geveent

New activity in ubergarm/MiMo-V2-Flash-GGUF 5 days ago

MiMo V2 Flash IQ5_K

👍 2

1

#1 opened 6 days ago by

geveent

New activity in bartowski/XiaomiMiMo_MiMo-V2-Flash-GGUF 5 days ago

thinking tag?

9

#1 opened 17 days ago by

gopi87

updated a model 6 days ago

ubergarm/MiMo-V2-Flash-GGUF

Text Generation • 309B • Updated 6 days ago • 164 • 1

published a model 7 days ago

ubergarm/MiMo-V2-Flash-GGUF

Text Generation • 309B • Updated 6 days ago • 164 • 1

liked 2 models 7 days ago

XiaomiMiMo/MiMo-V2-Flash

Text Generation • 310B • Updated 25 days ago • 35k • • 565

bartowski/XiaomiMiMo_MiMo-V2-Flash-GGUF

Text Generation • 309B • Updated 18 days ago • 4k • 7

New activity in yhavinga/GLM-4.7-REAP-40p-GGUF 8 days ago

the gguf working but need to reduce the gpu layers

👀 1

3

#2 opened 8 days ago by

gopi87

New activity in ubergarm/GLM-4.7-GGUF 8 days ago

Why does this double my PP and improve TG?

4

#9 opened 8 days ago by

gtkunit

anyone running via cpu+gpu+rpc gpu ?

3

#8 opened 13 days ago by

gopi87

liked a model 8 days ago

Qwen/Qwen-Image-2512

Text-to-Image • Updated 12 days ago • 25.1k • • 571

New activity in ubergarm/GLM-4.7-GGUF 12 days ago

Stable run on 2x RTX 5090 and 2 Xeon E5 2696 V4 and DDR4 with ik_llama.cpp - 6.1 t/s on IQ4_K and 5.1 t/s on IQ5_K, opencode works with this

👍 1

7

#5 opened 17 days ago by

martossien