John Leimgruber III's picture

John Leimgruber III

ubergarm

·

https://emptyduck.com

ubergarm

AI & ML interests

Open LLMs and Astrophotography image processing.

Recent Activity

liked a model about 7 hours ago

unsloth/gemma-3-27b-it-GGUF

new activity 1 day ago

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

new activity 1 day ago

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

View all activity

Organizations

None yet

ubergarm's activity

New activity in KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid 1 day ago

Documentation

#2 opened 1 day ago by

New activity in unsloth/QwQ-32B-unsloth-bnb-4bit 1 day ago

How to use the bnb-4bit model?

#4 opened 5 days ago by

New activity in Qwen/QwQ-32B 1 day 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

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

Q4KS

#4 opened 5 days ago by

New activity in KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid 4 days ago

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

#1 opened 7 days ago by

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

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

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

How about deepseek v3 model?

#15 opened 6 days ago by

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

Something wrong

#3 opened 8 days ago by

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

What languages were you trained in?

#7 opened 8 days ago by

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

Huh?

#1 opened 28 days ago by

New activity in unsloth/DeepSeek-R1-GGUF 27 days ago

Cannot Run `unsloth/DeepSeek-R1-GGUF` Model – Missing `configuration_deepseek.py`

#32 opened 27 days ago by

New activity in unsloth/DeepSeek-R1-GGUF about 1 month ago

No think tokens visible

#15 opened about 1 month ago by

Over 2 tok/sec agg backed by NVMe SSD on 96GB RAM + 24GB VRAM AM5 rig with llama.cpp

#13 opened about 1 month ago by

Got it running after downloading some RAM!

#7 opened about 1 month ago by

New activity in mradermacher/Qwen2.5-14B-Instruct-1M-i1-GGUF about 1 month ago

Over 128k context on 1x 3090 TI FE 24GB VRAM!

#1 opened about 1 month ago by

New activity in unsloth/DeepSeek-R1-GGUF about 1 month ago

Inference speed

#9 opened about 1 month ago by

New activity in HKUSTAudio/Llasa-3B about 2 months ago

Control over output

#12 opened about 2 months ago by

TeachableMachine

New activity in srinivasbilla/llasa-3b-tts about 2 months ago

Emotions

#3 opened about 2 months ago by

New activity in jinaai/ReaderLM-v2 about 2 months ago

What advantage does this have over normal algorithmic ways of turning HTML to Markdown ?

#5 opened about 2 months ago by