GGUF models by microtensor-archive
38 GGUF models quantized by microtensor-archive on Hugging Face. Sizes run from 178M to 3.84B parameters. The longest trained context is 128K tokens.
XL
mt support 3g r1240 5FnxoF33
Xlam · microtensor-archive
Params251M
Context32K
Smallest0.2 GB
LL
mt guard 4g r1241 5HaoFPqy
Llama · microtensor-archive
Params1.4B
Context128K
Smallest0.9 GB
EX
mt extract 3g r1237 5DS3cLo4
Extract · microtensor-archive
Params596M
Context40K
Smallest0.4 GB
QW
mt code 3g r1236 5HeK2i6J
Qwen · microtensor-archive
Params596M
Context40K
Smallest0.6 GB
QW
mt extract 3g r1237 5ED3LzEW
Qwen · microtensor-archive
Params596M
Context40K
Smallest0.4 GB
EX
mt extract 3g r1237 5EqFqFeD
Extract · microtensor-archive
Params439M
Context40K
Smallest0.3 GB
CO
mt code 3g r1238 5ED3LzEW
Code · microtensor-archive
Params1.54B
Context32K
Smallest1.0 GB
XL
mt support 3g r1240 5HEtPjha
Xlam · microtensor-archive
Params257M
Context32K
Smallest0.2 GB