Timon

KeyboardMasher

AI & ML interests

None yet

Recent Activity

new activity 37 minutes ago

unsloth/DeepSeek-R1-GGUF:Over 2 tok/sec agg backed by NVMe SSD on 96GB RAM + 24GB VRAM AM5 rig with llama.cpp

reacted to fdaudens's post with 😎 2 days ago

Yes, DeepSeek R1's release is impressive. But the real story is what happened in just 7 days after: - Original release: 8 models, 540K downloads. Just the beginning... - The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals. The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient. When you empower builders, innovation explodes. For everyone. 🚀 The most popular community model? @bartowski's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.

new activity 9 days ago

unsloth/DeepSeek-V3-GGUF:Issue with --n-gpu-layers 5 Parameter: Model Only Running on CPU

View all activity

Organizations

None yet

KeyboardMasher's activity

New activity in unsloth/DeepSeek-R1-GGUF 37 minutes ago

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

#13 opened about 21 hours ago by

ubergarm

New activity in unsloth/DeepSeek-V3-GGUF 9 days ago

Issue with --n-gpu-layers 5 Parameter: Model Only Running on CPU

#10 opened 18 days ago by

vuk123

New activity in unsloth/DeepSeek-V3-GGUF 10 days ago

Advice on running llama-server with Q2_K_L quant

#6 opened 21 days ago by

vmajor

I loaded DeepSeek-V3-Q5_K_M up on my 10yrs old old Tesla M40 (Dell C4130)

#8 opened 21 days ago by

gng2info

New activity in bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF about 1 month ago

Model will need to be requantized, rope issues for long context

#2 opened about 1 month ago by

treehugg3

New activity in allenai/OLMo-2-1124-7B-GGUF 2 months ago

Instruct version?

#1 opened 2 months ago by

KeyboardMasher

New activity in allenai/Llama-3.1-Tulu-3-8B 2 months ago

Feedback

#2 opened 2 months ago by

KeyboardMasher

New activity in Nexusflow/Athene-70B 3 months ago

we need llama athene 3.1 70b

#5 opened 6 months ago by

gopi87

New activity in bartowski/Qwen2.5.1-Coder-7B-Instruct-GGUF 3 months ago

Change the 'Original model' link to tree/9092a8a, which contains the updated weights.

#2 opened 3 months ago by

AaronFeng753

New activity in bartowski/Reflection-Llama-3.1-70B-GGUF 3 months ago

Remove this model from Recent highlights collection

#9 opened 3 months ago by

KeyboardMasher

New activity in bartowski/granite-3.0-8b-instruct-GGUF 3 months ago

Continuous output

#1 opened 3 months ago by

kth8

New activity in pabloce/dolphin-2.8-gemma-7b-GGUF 10 months ago

Q8_0 file is damaged.

#1 opened 10 months ago by

KeyboardMasher

Q8_0 file is damaged.

#1 opened 10 months ago by

KeyboardMasher