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.
QW
mt classify 3g r1239 5CLfzJdv
Qwen · microtensor-archive
Params197M
Context32K
Smallest0.2 GB
CO
mt code 3g r1238 5CkuRmNC
Code · microtensor-archive
Params494M
Context32K
Smallest0.5 GB
QW
mt code 3g r1236 5EEv1oLk
Qwen · microtensor-archive
Params596M
Context40K
Smallest0.5 GB
CO
mt code 3g r1238 5CLfzJdv
Code · microtensor-archive
Params494M
Context32K
Smallest0.4 GB
XL
mt support 3g r1240 5CUWFXGB
Xlam · microtensor-archive
Params608M
Context32K
Smallest0.4 GB
CO
mt code 3g r1238 5GVjqK3j
Code · microtensor-archive
Params494M
Context32K
Smallest1.0 GB
CO
mt code 3g r1238 5EyYXepK
Code · microtensor-archive
Params494M
Context32K
Smallest0.3 GB
CO
mt code 3g r1238 5DXHL1rx
Code · microtensor-archive
Params494M
Context32K
Smallest0.5 GB
LL
mt guard 4g r1241 5FLXTZox
Llama · microtensor-archive
Params229M
Context128K
Smallest0.2 GB
EX
mt extract 3g r1237 5EnrDrZg
Extract · microtensor-archive
Params407M
Context40K
Smallest0.3 GB
QW
mt code 3g r1236 5ELAnLj3
Qwen · microtensor-archive
Params752M
Context40K
Smallest0.8 GB
LL
mt guard 4g r1241 5G24BM47
Llama · microtensor-archive
Params495M
Context128K
Smallest0.3 GB
CO
mt code 3g r1236 5HKyjd9J
Code · microtensor-archive
Params596M
Context40K
Smallest0.6 GB
QW
mt classify 3g r1239 5DoaV8JK
Qwen · microtensor-archive
Params178M
Context32K
Smallest0.2 GB
CO
mt code 3g r1236 5GgkLbiy
Code · microtensor-archive
Params596M
Context40K
Smallest0.4 GB
XL
mt support 3g r1240 5DoaV8JK
Xlam · microtensor-archive
Params327M
Context32K
Smallest0.3 GB
LL
mt guard 4g r1241 5GVjqK3j
Llama · microtensor-archive
Params426M
Context128K
Smallest0.1 GB
XL
mt support 3g r1240 5EyYXepK
Xlam · microtensor-archive
Params374M
Context32K
Smallest0.3 GB
QW
mt extract 3g r1237 5FnxoF33
Qwen · microtensor-archive
Params1.72B
Context40K
Smallest1.1 GB
XL
mt support 3g r1240 5CLfzJdv
Xlam · microtensor-archive
Params280M
Context32K
Smallest0.2 GB
XL
mt support 3g r1240 5CcaCist
Xlam · microtensor-archive
Params270M
Context32K
Smallest0.2 GB
QW
mt classify 3g r1239 5EyYXepK
Qwen · microtensor-archive
Params178M
Context32K
Smallest0.2 GB
CO
mt code 3g r1236 5GCb9fhg
Code · microtensor-archive
Params596M
Context40K
Smallest0.5 GB
QW
mt classify 3g r1239 5CkuRmNC
Qwen · microtensor-archive
Params241M
Context32K
Smallest0.2 GB
CO
mt code 3g r1236 5DbzcvtB
Code · microtensor-archive
Params1.72B
Context40K
Smallest1.1 GB
CO
mt code 3g r1236 5EXH1GnJ
Code · microtensor-archive
Params1.72B
Context40K
Smallest1.5 GB
LL
mt guard 4g r1241 5HEtPjha
Llama · microtensor-archive
Params456M
Context128K
Smallest0.5 GB
PH
mt guard 4g r1241 5FjVGEKt
Phi · microtensor-archive
Params3.84B
Context128K
Smallest2.1 GB
LL
mt guard 4g r1241 5FZ6xLPT
Llama · microtensor-archive
Params3.21B
Context128K
Smallest2.0 GB
EX
mt extract 3g r1237 5DvkaYnL
Extract · microtensor-archive
Params517M
Context40K
Smallest0.3 GB
About microtensor-archive on Hugging Face
microtensor-archive has published 38 GGUF models that ggufmodels.com tracks, across families such as Code, Qwen and Xlam. The most downloaded are mt classify 3g r1239 5CLfzJdv, mt code 3g r1238 5CkuRmNC and mt code 3g r1236 5EEv1oLk.
Parameter counts run from 178M to 3.84B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has microtensor-archive published?
38 models are listed here, mainly from the Code, Qwen and Xlam families. The most downloaded is mt classify 3g r1239 5CLfzJdv.
Which quants does microtensor-archive publish?
See the model pages for the exact list of files.