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
OP
opencoder 1.5b instruct
Opencoder · neopolita
Params1.91B
Context4K
Q4_K_M1.4 GB
Coding
RA
rakutenai 7b chat
Rakutenai · neopolita
Params7.37B
Context32K
Q4_K_M4.5 GB
GGUF
DA
h2o danube 1.8b sft
Danube · neopolita
Params1.83B
Context16K
Q4_K_M1.1 GB
GGUF
ST
stable code instruct 3b
Stable · neopolita
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
MA
mathstral 7b v0.1
Mathstral · neopolita
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
CO
yi coder 9b
Coder · neopolita
Params8.83B
Context128K
Q4_K_M5.3 GB
Coding
DA
h2o danube 1.8b chat
Danube · neopolita
Params1.83B
Context16K
Q4_K_M1.1 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · neopolita
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
ST
starcoder2 15b instruct v0.1
StarCoder · neopolita
Params16B
Context16K
Q4_K_M9.9 GB
Coding
LL
llama 3.2 3b
Llama · neopolita
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
DE
deepseek r1 redistill qwen 1.5b v1.1
DeepSeek · neopolita
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
SM
smollm 135m instruct
SmolLM · neopolita
Params135M
Context2K
Q4_K_M0.1 GB
GGUF
MA
magpielm 4b sft v0.1
Magpielm · neopolita
Params4.51B
Context128K
Q4_K_M2.8 GB
GGUF
DE
deepseek prover v1.5 base
DeepSeek · neopolita
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
IN
instructlm 1.3b
Instructlm · neopolita
Params1.35B
Context2K
Q4_K_M0.8 GB
GGUF
QW
V22_4Bit
Qwen · neopolita
Params22.6B
Context256K
Q4_K_M14.0 GB
ReasoningTool use
MI
Neo-Ministral-3-3B-Instruct-2512
Mistral · neopolita
Params3.43B
Context256K
Smallest6.9 GB
Tool use
LL
meta llama 3.1 8b instruct
Llama · neopolita
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
QW
V23_2Bit
Qwen · neopolita
Params22.6B
Context256K
Q4_K_M14.0 GB
ReasoningTool use
LL
llama guard 3 1b
Llama · neopolita
Params1.5B
Context128K
Q4_K_M1.0 GB
GGUF
SM
smollm 1.7b instruct
SmolLM · neopolita
Params1.71B
Context2K
Q4_K_M1.1 GB
GGUF
LL
llama guard 3 8b
Llama · neopolita
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
QW
qwen2.5 7b
Qwen · neopolita
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
QW
qwen2 math 1.5b
Qwen · neopolita
Params1.54B
Context4K
Q4_K_M1.0 GB
GGUF
QW
Qwen3.6 35B A3B Saikei 8bit
Qwen · neopolita
Params34.7B
Context256K
Smallest36.9 GB
ReasoningTool use
AY
aya expanse 8b
Aya · neopolita
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF
DE
deepseek r1 redistill qwen 1.5b v1.0
DeepSeek · neopolita
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
AR
arcee scribe
Arcee · neopolita
Params7.74B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Niwaki Qwen3.6 27B A3B v3.0
Qwen · neopolita
Params26.6B
Context256K
Smallest12.8 GB
ReasoningTool use
CE
cerebrum 1.0 7b
Cerebrum · neopolita
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

Keep browsing