Hugging Face's logo

ubergarm
/
DeepSeek-R1-0528-GGUF

Text Generation
GGUF
mla
imatrix
conversational
ik_llama.cpp
Model card Files
xet
Community
19
DeepSeek-R1-0528-GGUF

Commit History

Delete imatrix-v02-Qwen3-14B-BF16.dat
c8c4d22
verified

ubergarm commited on

Upload imatrix-v02-Qwen3-14B-BF16.dat with huggingface_hub
e06d553
verified

ubergarm commited on

Upload folder using huggingface_hub
9e2eae7
verified

ubergarm commited on

Add IQ3_KS quant perplexity and details
84d15ba

ubergarm commited on

Add note that ik_llama.cpp can run any regular GGUF
3bdf2b0

ubergarm commited on

Upload folder using huggingface_hub
848a152
verified

ubergarm commited on

Update readme for multiGPU and IQ1_S_R4
076fc03

ubergarm commited on

Add recommended sampling --temp 0.6 --top-p 0.95
0b7aeed

ubergarm commited on

World's smallest working R1-0528 Quant!
88495ef

ubergarm commited on

Add IQ1_S to support CUDA offload.
f740b23

ubergarm commited on

Upload folder using huggingface_hub
fc9f8e9
verified

ubergarm commited on

Upload folder using huggingface_hub
77f6502
verified

ubergarm commited on

Add IQ1_S_R4 and IQ4_KS_R4 and secret meme
869d411

ubergarm commited on

Upload folder using huggingface_hub
f07ee20
verified

ubergarm commited on

the IQ2_K_R4 just uploaded!
87f8292

ubergarm commited on

Upload folder using huggingface_hub
a43a415
verified

ubergarm commited on

release IQ3_K_R4! ooh yeah!
f51f0fc

ubergarm commited on

Upload folder using huggingface_hub
66f78c5
verified

ubergarm commited on

Upload /imatrix-DeepSeek-R1-0528.dat with huggingface_hub
c59dfc4
verified

ubergarm commited on

getting closer
07aaa83

ubergarm commited on

Fixup README
9e46a55

ubergarm commited on

quants still cookin'
efd8628

ubergarm commited on