GGUF models by Manojb
345 GGUF models quantized by Manojb on Hugging Face. Sizes run from 331M to 79.7B parameters. The longest trained context is 488K tokens.
LI
Ling Coder Lite
Ling · Manojb
Params16.8B
Context4K
Smallest12.7 GB
NA
nanbeige4.1 python deepthink fp16
Nanbeige · Manojb
Params3.93B
Context256K
Smallest7.9 GB
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Q4_K_M9.9 GB
HU
Huihui Ling Mini 2.0 Abliterated
Huihui · Manojb
Params16.3B
Context32K
Smallest10.3 GB
ME
MechaEpstein 8000M Q4 K M
Mechaepstein · Manojb
Params8.19B
Context40K
Q4_K_M5.0 GB
HU
Huihui Ling Mini 2.0 Abliterated
Huihui · Manojb
Params16.3B
Context32K
Smallest11.6 GB
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Smallest13.5 GB
GL
Gpt Oss 20b Glm 4.6 Distill
GLM · Manojb
Params20.9B
Context128K
Smallest13.8 GB
HU
Huihui Ling Mini 2.0 Abliterated
Huihui · Manojb
Params16.3B
Context32K
Smallest11.3 GB
HU
Huihui Ling Mini 2.0 Abliterated
Huihui · Manojb
Params16.3B
Context32K
Smallest9.3 GB
QW
Qwen3 14B GPT 5.2 Distill.iq4 nl
Qwen · Manojb
Params14.8B
Context40K
Smallest8.6 GB
NE
Nemotron Cascade 8B Thinking.Q8 0
Nemotron · Manojb
Params8.19B
Context32K
Smallest8.7 GB
GL
Gpt Oss 20b Glm 4.6 Distill
GLM · Manojb
Params20.9B
Context128K
Smallest12.1 GB
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Smallest11.6 GB
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Smallest8.8 GB