GGUF models by neopolita
183 GGUF models quantized by neopolita on Hugging Face. Sizes run from 135M to 177B parameters. The longest trained context is 256K tokens.
PH
phi 3 medium 128k instruct
Phi · neopolita
Params14B
Context128K
Q4_K_M8.6 GB
QW
V22_2Bit
Qwen · neopolita
Params22.6B
Context256K
Q4_K_M14.0 GB
QW
qwen2.5 math 7b instruct
Qwen · neopolita
Params7.62B
Context4K
Q4_K_M4.7 GB
LL
meta llama 3.1 8b
Llama · neopolita
Params8.03B
Context128K
Q4_K_M4.9 GB
LL
llama 3.2 1b
Llama · neopolita
Params1.24B
Context128K
Q4_K_M0.8 GB
QW
qwen2 1.5b
Qwen · neopolita
Params1.54B
Context128K
Q4_K_M1.0 GB
QW
qwen2.5 math 1.5b
Qwen · neopolita
Params1.54B
Context4K
Q4_K_M1.0 GB
QW
Qwen2.5 7B Instruct
Qwen · neopolita
Params7.62B
Context32K
Q4_K_M4.7 GB
DE
deepseek prover v1.5 rl
DeepSeek · neopolita
Params6.91B
Context4K
Q4_K_M4.2 GB
MA
magpielm 8b sft v0.1
Magpielm · neopolita
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
V21_4Bit
Qwen · neopolita
Params22.6B
Context256K
Q4_K_M14.0 GB
QW
Qwen3.6 27B A3B Niwaki 2bit
Qwen · neopolita
Params26.6B
Context256K
Q4_K_M17.8 GB
QW
liberated qwen1.5 72b
Qwen · neopolita
Params72.3B
Context32K
Q4_K_M44.1 GB
VI
Virtuoso Small v2
Virtuoso · neopolita
Params14.8B
Context128K
Q4_K_M9.0 GB
OP
opencoder 1.5b base
Opencoder · neopolita
Params1.91B
Context4K
Q4_K_M1.4 GB
YI
yi 1.5 9b chat
Yi · neopolita
Params8.83B
Context4K
Q4_K_M5.3 GB
LL
llama 3.1 hawkish 8b
Llama · neopolita
Params8.03B
Context128K
Q4_K_M4.9 GB
DE
deepseek prover v1.5 sft
DeepSeek · neopolita
Params6.91B
Context4K
Q4_K_M4.2 GB
QW
Qwen3.6 19B A3B Niwaki 2bit
Qwen · neopolita
Params18.6B
Context256K
Q4_K_M11.4 GB
SM
smollm 1.7b
SmolLM · neopolita
Params1.71B
Context2K
Q4_K_M1.1 GB
SH
shieldgemma 2b
Shieldgemma · neopolita
Params2.61B
Context8K
Q4_K_M1.7 GB
QW
Qwen3.6 19B A3B Niwaki v2 2bit
Qwen · neopolita
Params34.7B
Context256K
Q4_K_M14.8 GB
CO
yi coder 1.5b
Coder · neopolita
Params1.48B
Context128K
Q4_K_M1.0 GB
QW
Qwen2.5 14B Instruct
Qwen · neopolita
Params14.8B
Context32K
Q4_K_M9.0 GB
XV
xverse 7b
Xverse · neopolita
Params7.3B
Context8K
Q4_K_M4.5 GB
QW
V21_2Bit
Qwen · neopolita
Params22.6B
Context256K
Q4_K_M14.0 GB
QW
qwen2 0.5b instruct
Qwen · neopolita
Params494M
Context32K
Q4_K_M0.4 GB
MI
mistral small instruct 2409
Mistral · neopolita
Params22.2B
Context32K
Q4_K_M13.3 GB
DE
deepseek r1 redistill qwen 7b v1.1
DeepSeek · neopolita
Params7.62B
Context128K
Q4_K_M4.7 GB
QW
Qwen3.6 19B A3B Niwaki v2 4bit
Qwen · neopolita
Params34.7B
Context256K
Q4_K_M14.8 GB