GGUF models by DevQuasar-13
36 GGUF models quantized by DevQuasar-13 on Hugging Face. Sizes run from 494M to 405B parameters. The longest trained context is 2096K tokens.
NE
OpenMath Nemotron 7B
Nemotron · DevQuasar-13
Params7.62B
Context128K
Q4_K_M4.7 GB
GE
Google.Gemma 3 1b It
Gemma · DevQuasar-13
Params1B
Context32K
Q4_K_M0.8 GB
LL
Llama xLAM 2 70b Fc R
Llama · DevQuasar-13
Params70.6B
Context128K
Q4_K_M42.5 GB
SQ
Sqlcoder 34b
Sqlcoder · DevQuasar-13
Params33.7B
Context16K
Q4_K_M20.2 GB
OL
tngtech.OLMo 2 Instruct Math 32B
OLMo · DevQuasar-13
Params32.2B
Context4K
Q4_K_M19.5 GB
LL
Llama xLAM 2 8b Fc R
Llama · DevQuasar-13
Params8.03B
Context128K
Q4_K_M4.9 GB
TE
openGPT X.Teuken 7B Instruct Commercial v0.4
Teuken · DevQuasar-13
Params7.45B
Context4K
Q4_K_M5.0 GB
SM
HuggingFaceTB.SmolLM2 1.7B Instruct 16k
SmolLM · DevQuasar-13
Params1.71B
Context16K
Q4_K_M1.1 GB