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 5 hours ago

bartowski/THUDM_GLM-Z1-32B-0414-GGUF

liked a model about 17 hours ago

Skywork/SkyReels-V2-I2V-14B-540P

upvoted a collection about 17 hours ago

View all activity

Organizations

None yet

ubergarm's activity

New activity in ubergarm/gemma-3-27b-it-qat-GGUF 2 days ago

Try to install for ollama but got errors

#1 opened 3 days ago by

New activity in Comfy-Org/HiDream-I1_ComfyUI 3 days ago

Can we have a Llama-3.1-8B-Lexi-Uncensored-V2_fp8_scaled.safetensors

#10 opened 8 days ago by

New activity in bartowski/google_gemma-3-27b-it-qat-GGUF 4 days ago

Other Imatrix quants (IQ3_XS) ?

#1 opened 5 days ago by

New activity in city96/HiDream-I1-Full-gguf 5 days ago

Can we use existed llama 3.1 gguf

#1 opened 8 days ago by

New activity in google/gemma-3-27b-it-qat-q4_0-unquantized 5 days ago

Some initial results comparing size and perplexity

#1 opened 6 days ago by

New activity in google/gemma-3-12b-it-qat-q4_0-gguf 6 days ago

Permission to access the Unquantized versions of the QAT weights for Gemma-3

#4 opened 18 days ago by

New activity in google/gemma-3-27b-it-qat-q4_0-gguf 6 days ago

why is the size bigger than regular Q4_0 quants ?

#1 opened 21 days ago by

New activity in ubergarm/DeepSeek-V3-0324-GGUF 22 days ago

Expected speed in some known hardware - data required

#1 opened 22 days ago by

New activity in mradermacher/DeepSeek-V3-0324-i1-GGUF 23 days ago

Model card side-bar missing?

#1 opened 26 days ago by

New activity in mradermacher/model_requests 25 days ago

https://huggingface.co/deepseek-ai/DeepSeek-V3-0324

#797 opened about 1 month ago by

New activity in daydream-org/DeepSeek-R1-GGUF-11446 about 1 month ago

Possible to upload Q4_K_M?

#1 opened 3 months ago by

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

How to use the bnb-4bit model?

#4 opened about 2 months ago by

New activity in Qwen/QwQ-32B about 1 month ago

我的3090TI 24GB显存运行非常愉快！感谢开发团队！

#11 opened about 2 months ago by

New activity in unsloth/QwQ-32B-GGUF about 1 month ago

Q4KS

#4 opened about 2 months ago by

New activity in KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid about 2 months ago

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

#1 opened about 2 months ago by

New activity in meituan/DeepSeek-R1-Block-INT8 about 2 months ago

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

#17 opened about 2 months ago by

New activity in unsloth/DeepSeek-R1-GGUF about 2 months 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 about 2 months ago by

New activity in meituan/DeepSeek-R1-Block-INT8 about 2 months ago

How about deepseek v3 model?

#15 opened about 2 months ago by

New activity in bartowski/Qwen_QwQ-32B-GGUF about 2 months ago

Something wrong

#3 opened about 2 months ago by

New activity in Qwen/QwQ-32B about 2 months ago

What languages were you trained in?

#7 opened about 2 months ago by