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.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8 Flash Next 99B A5B Niwaki 3bit
Qwen · neopolita
Params105B
Context256K
Smallest42.5 GB
GGUF
MI
mistral 7b v0.1
Mistral · neopolita
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3.8-Flash-Next-102B-A5B-Niwaki-v2.4-3bit
Qwen · neopolita
Params108B
Context256K
Smallest43.8 GB
GGUF
QW
Qwen3.8-Flash-Next-119B-A5B-Niwaki-v2.4-3bit
Qwen · neopolita
Params118B
Context256K
Smallest51.0 GB
ReasoningTool use
QW
Qwen3.8-Flash-Next-113B-A5B-Niwaki-3bit
Qwen · neopolita
Params121B
Context256K
Smallest49.1 GB
ReasoningTool use
QW
Niwaki Qwen3.8 Flash Next 141B A6B v4.0
Qwen · neopolita
Params141B
Context256K
Smallest61.7 GB
ReasoningTool use
QW
Niwaki Qwen3.6 30B A3B v3.0
Qwen · neopolita
Params30B
Context256K
Smallest14.1 GB
ReasoningTool use
QW
qwen2.5 0.5b
Qwen · neopolita
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
QW
Qwen3.6 11B A3B Niwaki 4bit
Qwen · neopolita
Params10.5B
Context256K
Q4_K_M7.0 GB
ReasoningTool use
ST
starcoder2 3b
StarCoder · neopolita
Params3.03B
Context16K
Q4_K_M1.9 GB
Coding
ST
starcoder2 15b
StarCoder · neopolita
Params16B
Context16K
Q4_K_M9.9 GB
Coding
QW
qwen2.5 coder 1.5b
Qwen · neopolita
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
LL
meta llama 3 8b instruct
Llama · neopolita
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
NI
Niwaki Flash Next 23GB v4.0
Niwaki · neopolita
Params131B
Context256K
Smallest40.2 GB
ReasoningTool use
SM
smollm 135m
SmolLM · neopolita
Params135M
Context2K
Q4_K_M0.1 GB
GGUF
YI
yi 34b
Yi · neopolita
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
QW
Qwen3.8-Flash-Next-Saikei-v1.0
Qwen · neopolita
Params177B
Context256K
Smallest101.4 GB
ReasoningTool use
QW
qwen2.5 1.5b instruct
Qwen · neopolita
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
CO
yi coder 1.5b chat
Coder · neopolita
Params1.48B
Context128K
Q4_K_M1.0 GB
Coding
QW
qwen2.5 coder 7b
Qwen · neopolita
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
LL
llama 3.2 1b instruct
Llama · neopolita
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
QW
V23_4Bit
Qwen · neopolita
Params22.6B
Context256K
Q4_K_M14.0 GB
ReasoningTool use
OP
opencoder 8b base
Opencoder · neopolita
Params7.77B
Context8K
Q4_K_M4.7 GB
Coding
FI
firefunction v1
Firefunction · neopolita
Params46.7B
Context32K
Q4_K_M28.4 GB
Tool use
CE
cerebrum 1.0 8x7b
Cerebrum · neopolita
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
QW
qwen2.5 coder 1.5b instruct
Qwen · neopolita
Params1.54B
Context32K
Q4_K_M1.0 GB
CodingTool use
OL
olmo 1.7 7b hf
OLMo · neopolita
Params6.89B
Context4K
Q4_K_M4.2 GB
GGUF
LL
finance llama3 8b
Llama · neopolita
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
codestral 22b v0.1
Mistral · neopolita
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
ST
starcoder2 7b
StarCoder · neopolita
Params7.17B
Context16K
Q4_K_M4.5 GB
Coding

About neopolita on Hugging Face

neopolita has published 183 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Yi. The most downloaded are Qwen3.8 Flash Next 99B A5B Niwaki 3bit, mistral 7b v0.1 and Qwen3.8-Flash-Next-102B-A5B-Niwaki-v2.4-3bit.

The quants neopolita publishes most often are Q4_K_M (156), Q8_0 (147), Q3_K_M (145) and Q2_K (145). Their Q4_K_M files range from 0.1 to 44.1 GB. Parameter counts run from 135M to 177B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has neopolita published?

183 models are listed here, mainly from the Qwen, Llama and Yi families. The most downloaded is Qwen3.8 Flash Next 99B A5B Niwaki 3bit.

Which quants does neopolita publish?

The most common are Q4_K_M (156 models), Q8_0 (147 models), Q3_K_M (145 models) and Q2_K (145 models).

Keep browsing