45 9 126

John Leimgruber III

ubergarm

https://emptyduck.com

ubergarm

AI & ML interests

Open LLMs and Astrophotography image processing.

Recent Activity

new activity about 20 hours ago

KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid:Documentation

new activity about 22 hours ago

unsloth/QwQ-32B-unsloth-bnb-4bit:How to use the bnb-4bit model?

new activity about 22 hours ago

Qwen/QwQ-32B:我的3090TI 24GB显存运行非常愉快！感谢开发团队！

View all activity

Organizations

None yet

ubergarm's activity

New activity in KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid about 20 hours ago

Documentation

#2 opened about 20 hours ago by

ubergarm

New activity in unsloth/QwQ-32B-unsloth-bnb-4bit about 22 hours ago

How to use the bnb-4bit model?

#4 opened 5 days ago by

neoragex2002

New activity in Qwen/QwQ-32B about 22 hours ago

我的3090TI 24GB显存运行非常愉快！感谢开发团队！

#11 opened 8 days ago by

ubergarm

upvoted a collection 2 days ago

FP8 LLMs for vLLM

Collection

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated Oct 17, 2024 • 67

New activity in unsloth/QwQ-32B-GGUF 3 days ago

Q4KS

#4 opened 5 days ago by

Alastar-Smith

New activity in KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid 3 days ago

DeepSeek-R1-UD-IQ1_M-FP8 : Support and Perf Results on v0.2.3

#1 opened 7 days ago by

shawxysu

liked a model 4 days ago

unsloth/QwQ-32B-GGUF

Text Generation • Updated 3 days ago • 84k • 58

New activity in meituan/DeepSeek-R1-Block-INT8 4 days ago

Optimal `weight_block_size` for Intel AMX `amx_int8` `amx_tile`?

#17 opened 4 days ago by

ubergarm

New activity in unsloth/DeepSeek-R1-GGUF 5 days ago

DeepSeek-R1-UD-Q2_K_XL model inference by llama.cpp can't use flash-attention with n_embd_head_k!=n_embd_head_v

#43 opened 5 days ago by

fuzhenxin

liked a model 5 days ago

meituan/DeepSeek-R1-Block-INT8

Text Generation • Updated 14 days ago • 3.49k • 32

New activity in meituan/DeepSeek-R1-Block-INT8 5 days ago

How about deepseek v3 model?

#15 opened 6 days ago by

JohnnyBoyzzz

liked a model 6 days ago

Qwen/QwQ-32B-AWQ

Text Generation • Updated 2 days ago • 72.4k • 83

New activity in bartowski/Qwen_QwQ-32B-GGUF 8 days ago

Something wrong

#3 opened 8 days ago by

wcde

New activity in Qwen/QwQ-32B 8 days ago

What languages were you trained in?

#7 opened 8 days ago by

NickyNicky

liked 2 models 8 days ago

Qwen/QwQ-32B

Text Generation • Updated 2 days ago • 256k • • 2.1k

bartowski/Qwen_QwQ-32B-GGUF

Text Generation • Updated 8 days ago • 159k • 139

liked a model 10 days ago

bartowski/DeepSeek-R1-GGUF

Text Generation • Updated Jan 22 • 61.7k • 96

liked a model 15 days ago

KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid

Updated 9 days ago • 11

liked a model 22 days ago

unsloth/r1-1776-GGUF

Text Generation • Updated 22 days ago • 36.3k • 95

New activity in is210379/DeepSeek-R1-UD-IQ1_S 27 days ago

Huh?

#1 opened 28 days ago by

Nycnt

John Leimgruber III

AI & ML interests

Recent Activity

Organizations

ubergarm's activity

Documentation

How to use the bnb-4bit model?

我的3090TI 24GB显存运行非常愉快！感谢开发团队！

Q4KS

DeepSeek-R1-UD-IQ1_M-FP8 : Support and Perf Results on v0.2.3

Optimal `weight_block_size` for Intel AMX `amx_int8` `amx_tile`?

DeepSeek-R1-UD-Q2_K_XL model inference by llama.cpp can't use flash-attention with n_embd_head_k!=n_embd_head_v

How about deepseek v3 model?

Something wrong

What languages ​​were you trained in?

Huh?

What languages were you trained in?