GGUF models by NikolayKozloff

1011 GGUF models quantized by NikolayKozloff on Hugging Face. Sizes run from 30M to 33.1B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
GI
GigaChat3 10B A1.8B
Gigachat · NikolayKozloff
Params10.7B
Context256K
Q4_K_M6.5 GB
GGUF
LL
Llama 3.1 Minitron 4B Width Base
Llama · NikolayKozloff
Params4.51B
Context128K
Smallest4.8 GB
GGUF
MI
Minerva 3B Instruct v1.0 Q5 K M
Minerva · NikolayKozloff
Params2.89B
Context16K
Smallest2.1 GB
GGUF
FA
falcon 7b
Falcon · NikolayKozloff
Params7.22B
Context—
Smallest4.1 GB
GGUF
SA
SambaLingo Russian Chat
Sambalingo · NikolayKozloff
Params6.95B
Context4K
Smallest7.4 GB
GGUF
TR
Trendyol-LLM-7b-chat-v1.8
Trendyol · NikolayKozloff
Params7.34B
Context32K
Smallest4.2 GB
GGUF
GL
GLM 4.6V Flash
GLM · NikolayKozloff
Params9.4B
Context128K
Smallest7.1 GB
Vision
GE
Gemma-2-9B-It-SPPO-Iter3
Gemma · NikolayKozloff
Params9.24B
Context8K
Smallest5.4 GB
GGUF
NA
Nanbeige2-16B-Chat
Nanbeige · NikolayKozloff
Params15.8B
Context4K
Smallest11.2 GB
GGUF
GE
Gemma 3 12b It
Gemma · NikolayKozloff
Params11.8B
Context128K
Smallest8.2 GB
Vision
MI
Mistral Nemo Instruct 2407
Mistral · NikolayKozloff
Params12.2B
Context1000K
Smallest8.7 GB
GGUF
RO
RoLlama3-8b-Instruct
Rollama · NikolayKozloff
Params8.03B
Context8K
Smallest5.6 GB
GGUF
CZ
Czech-GPT-2-XL-133k
Czech · NikolayKozloff
Params1.78B
Context1K
Smallest1.9 GB
GGUF
QW
Qwen3 15B A2B Base
Qwen · NikolayKozloff
Params15.6B
Context4K
Smallest8.9 GB
Tool use
TW
tweety-7b-armenian-v24a
Tweety · NikolayKozloff
Params7.24B
Context32K
Smallest7.7 GB
GGUF
LL
Llama 3.1 8B Instruct bnb 4bit shqip Q8 0
Llama · NikolayKozloff
Params8.03B
Context128K
Smallest8.5 GB
Tool use
QW
Replete LLM V2.5 Qwen 32b
Qwen · NikolayKozloff
Params32.8B
Context32K
Smallest14.4 GB
Tool use
QW
Qwen2-7B
Qwen · NikolayKozloff
Params7.62B
Context128K
Smallest8.1 GB
GGUF
PH
phi 3 portuguese tom cat 4k instruct Q8 0
Phi · NikolayKozloff
Params3.82B
Context4K
Smallest4.1 GB
GGUF
LL
DeepHermes 3 Llama 3 8B Preview Q8 0
Llama · NikolayKozloff
Params8.03B
Context128K
Smallest8.5 GB
ReasoningRoleplayTool use
FA
Falcon
Falcon · NikolayKozloff
Params4.94B
Context2K
Smallest5.2 GB
GGUF
FI
Fimbulvetr-11B-v2.1-16K
Fimbulvetr · NikolayKozloff
Params10.7B
Context16K
Smallest6.1 GB
GGUF
MI
Mistral portuguese luana 7b Mathematics
Mistral · NikolayKozloff
Params7.24B
Context32K
Smallest7.7 GB
GGUF
GR
granite-3b-code-instruct
Granite · NikolayKozloff
Params3.48B
Context2K
Smallest3.7 GB
CodingTool use
MI
Mistral Small Instruct 2409
Mistral · NikolayKozloff
Params22.2B
Context128K
Smallest8.3 GB
GGUF
NE
Nemotron Mini 4B Instruct Q8 0
Nemotron · NikolayKozloff
Params4.19B
Context4K
Smallest4.5 GB
Tool use
IN
JanusCoder 14B
InternLM · NikolayKozloff
Params14.8B
Context32K
Smallest10.3 GB
CodingVision
DE
DeepSeek R1 Distill Llama 8B
DeepSeek · NikolayKozloff
Params8.03B
Context128K
Smallest8.5 GB
ReasoningTool use
GL
GLM 4.6V Flash
GLM · NikolayKozloff
Params9.4B
Context128K
Smallest10.0 GB
Vision
MI
Minerva 350M base v1.0 Q6 K
Minerva · NikolayKozloff
Params352M
Context16K
Smallest0.4 GB
GGUF

Keep browsing