GGUF models by Agnuxo
93 GGUF models quantized by Agnuxo on Hugging Face. Sizes run from 4M to 12.2B parameters. The longest trained context is 1000K tokens.
TI
Tinytron TinyLlama Instruct CODE Python Spanish English GGUF q5 k
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest0.8 GB
TI
Tinytron 1B TinyLlama Instruct CODE Python Spanish English GGUF q6 k
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest0.9 GB
MI
Mistral NeMo Minitron 8B Alpaca CODE Python GGUF 8bit
Mistral · Agnuxo
Params8.41B
Context8K
Smallest8.9 GB
LL
Llama 3.1 Minitron 4B Instruct CODE Python Spanish English GGUF 16bit
Llama · Agnuxo
Params4.54B
Context128K
Smallest9.1 GB
QW
Qwen2 1.5B Instruct MOE CODE assistant GGUF 8bit
Qwen · Agnuxo
Params1.54B
Context32K
Smallest1.6 GB
CA
cajal 9b v2 q4 k m
Cajal · Agnuxo
Params8.95B
Context256K
Q4_K_M5.6 GB
TI
Tinytron ORCA 3B Instruct CODE Python Spanish English GGUF 4bit
Tinytron · Agnuxo
Params1.1B
Context2K
Q4_K_M0.7 GB
TI
Tinytron 1B TinyLlama Instruct CODE Python Spanish English GGUF 4bit
Tinytron · Agnuxo
Params1.1B
Context2K
Q4_K_M0.7 GB
LL
Meta Llama 3.1 8B CODE Alpaca Python 8bit
Llama · Agnuxo
Params8.03B
Context128K
Smallest8.5 GB
QW
Qwen2 0.5B Spanish English raspberry pi GGUF 16bit
Qwen · Agnuxo
Params494M
Context128K
Smallest1.0 GB
QW
Qwen2 1.5B Instruct MOE assistant GGUF 16bit
Qwen · Agnuxo
Params1.54B
Context32K
Smallest3.1 GB
QW
Qwen2 7B Instruct CODE Python GGUF Spanish English 8bit
Qwen · Agnuxo
Params7.62B
Context32K
Smallest8.1 GB
TI
Tinytron TinyLlama Instruct CODE Python Spanish English GGUF 16bit
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest2.2 GB
TI
Tinytron ORCA 3B Instruct CODE Python English Asistant 16bit v2
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest2.2 GB
LL
Tiny Llama
Llama · Agnuxo
Params4M
Context2K
Q4_K_M0.0 GB
GE
gemma 2 2b instruct python CODE assistant GGUF 16bit
Gemma · Agnuxo
Params2.61B
Context8K
Smallest5.2 GB
TI
Tinytron TinyLlama Instruct CODE Python Spanish English GGUF 4bit
Tinytron · Agnuxo
Params1.1B
Context2K
Q4_K_M0.7 GB
QW
Qwen2 7B v2 Instruct CODE Python GGUF Spanish English 8bit
Qwen · Agnuxo
Params7.62B
Context32K
Smallest8.1 GB
TI
Tinytron 1B TinyLlama Instruct CODE Python Spanish English GGUF 16bit
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest2.2 GB
LL
Agente Llama 3.1 GGUF 16bit
Llama · Agnuxo
Params8.03B
Context128K
Smallest16.1 GB
LL
Agente Llama 3.1 Spanish English GGUF 4bit
Llama · Agnuxo
Params8.03B
Context128K
Q4_K_M4.9 GB
TI
Tinytron TinyLlama Instruct CODE Python GGUF Spanish English 8bit
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest1.2 GB
TI
Tinytron ORCA 3B Instruct CODE Python GGUF Spanish English 8bit
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest1.2 GB
LL
Agente Llama 3.1 Spanish 8bit
Llama · Agnuxo
Params8.03B
Context128K
Smallest8.5 GB
QW
Qwen2 0.5B GGUF Spanish English raspberry pi 8bit
Qwen · Agnuxo
Params494M
Context128K
Smallest0.5 GB
TI
Tinytron ORCA 7B Instruct CODE Python GGUF Spanish English 8bit
Tinytron · Agnuxo
Params6.74B
Context4K
Smallest7.2 GB
TI
Tinytron 1B TinyLlama Instruct CODE Python GGUF Spanish English 8bit
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest1.2 GB
LL
Tiny Llama
Llama · Agnuxo
Params4M
Context2K
Smallest0.0 GB
TI
Tinytron TinyLlama Instruct CODE Python Spanish English GGUF q6 k
Tinytron · Agnuxo
Params1.1B
Context2K
Smallest0.9 GB
LL
Tiny Llama
Llama · Agnuxo
Params4M
Context2K
Smallest0.0 GB