Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
wredd
/
medgemma-4b-gguf
like
1
GGUF
medical
quantized
llama.cpp
african-healthcare
imatrix
conversational
License:
gemma
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
medgemma-4b-gguf
6.82 GB
1 contributor
History:
7 commits
wredd
Add MedGemma IQ1_M - Extreme compression with African healthcare imatrix (~0.7GB)
e104e89
verified
5 days ago
.gitattributes
Safe
1.76 kB
Add MedGemma IQ1_M - Extreme compression with African healthcare imatrix (~0.7GB)
5 days ago
README.md
Safe
1.7 kB
Update model card with IQ2_XS and African healthcare focus
5 days ago
medgemma-4b-iq1_m.gguf
1.2 GB
xet
Add MedGemma IQ1_M - Extreme compression with African healthcare imatrix (~0.7GB)
5 days ago
medgemma-4b-iq2_xs.gguf
1.4 GB
xet
Add MedGemma 4B IQ2_XS - Ultra-compressed with African medical imatrix (~0.9GB)
5 days ago
medgemma-4b-q2_k.gguf
1.73 GB
xet
Add MedGemma 4B Q2_K (2-bit) for budget Android phones
6 days ago
medgemma-4b-q4_k_m.gguf
2.49 GB
xet
Add MedGemma 4B Q4_K_M (INT4) for standard devices
6 days ago
