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.

Most downloadedNewestLargestLongest contextSmallest
CA
CAJAL 4B Merged 16bit
Cajal · Agnuxo
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
MI
Mamba Codestral 7B v0.1 instruct python coding assistant GGUF 4bit
Mistral · Agnuxo
Params7.25B
Context32K
Q4_K_M4.4 GB
Coding
PH
Phi 3.5 mini instruct python coding assistant GGUF 16bit
Phi · Agnuxo
Params3.82B
Context128K
Smallest7.6 GB
Coding
QW
Agente GPT Qwen2.5 3B Instruct Spanish 8bit
Qwen · Agnuxo
Params3.4B
Context32K
Smallest3.6 GB
Tool use
QW
Agente GPT Qwen2.5 3B Instruct Spanish English GGUF q6 k
Qwen · Agnuxo
Params3.4B
Context32K
Smallest2.8 GB
Tool use
PH
Phi 3.5 mini instruct python coding assistant GGUF 4bit
Phi · Agnuxo
Params3.82B
Context128K
Q4_K_M2.3 GB
Coding
LL
Llama 3.1 Minitron 4B Instruct CODE Python GGUF Spanish English 8bit
Llama · Agnuxo
Params4.54B
Context128K
Smallest4.8 GB
Coding
QW
Qwen2 1.5B Instruct MOE Director GGUF 4bit
Qwen · Agnuxo
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
Agente GPT Qwen2.5 3B Instruct Spanish English GGUF 4bit
Qwen · Agnuxo
Params3.4B
Context32K
Q4_K_M2.1 GB
Tool use
QW
Qwen2 1.5B Instruct MOE CODE assistant GGUF 4bit
Qwen · Agnuxo
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
MI
Mamba Codestral 7B v0.1 python coding assistant GGUF 8bit
Mistral · Agnuxo
Params7.25B
Context32K
Smallest7.7 GB
Coding
QW
Agente GPT Qwen 2.5 7B Spanish 8bit
Qwen · Agnuxo
Params7.62B
Context128K
Smallest8.1 GB
Tool use
MI
Mistral Nemo CODE Python assistant GGUF 16bit
Mistral · Agnuxo
Params12.2B
Context1000K
Smallest24.5 GB
Coding
MI
Mamba Codestral 7B Instruct CODE Python Spanish English GGUF 4bit
Mistral · Agnuxo
Params7.25B
Context32K
Q4_K_M4.4 GB
Coding
MI
Mistral Nemo CODE Python assistant GGUF 8bit
Mistral · Agnuxo
Params12.2B
Context1000K
Smallest13.0 GB
Coding
QW
Agente GPT Qwen2.5 3B Instruct Spanish English GGUF q5 k
Qwen · Agnuxo
Params3.4B
Context32K
Smallest2.4 GB
Tool use
LL
Llama 3.1 Minitron 4B Instruct CODE Python Spanish English GGUF q5 k
Llama · Agnuxo
Params4.54B
Context128K
Smallest3.3 GB
Coding
QW
Agente Director Qwen2 7Bron Instruct CODE Python English GGUF 16bit
Qwen · Agnuxo
Params7.62B
Context32K
Smallest15.2 GB
Coding
MI
Mistral NeMo Minitron 8B Alpaca CODE Python GGUF 16bit
Mistral · Agnuxo
Params8.41B
Context8K
Smallest16.8 GB
Coding
QW
Agente Director Qwen2 7B Instruct CODE Python Spanish English GGUF q6 k
Qwen · Agnuxo
Params7.62B
Context32K
Smallest6.3 GB
Coding
QW
Qwen2 1.5B Instruct MOE BIOLOGY assistant GGUF 4bit
Qwen · Agnuxo
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
QW
Agente GPT Qwen 2.5 3B Spanish English GGUF 32bit
Qwen · Agnuxo
Params3.4B
Context32K
Smallest13.6 GB
Tool use
CA
cajal 9b v2 f16
Cajal · Agnuxo
Params8.95B
Context256K
Smallest17.9 GB
ReasoningTool use
QW
Agente GPT Qwen 2.5 7B Spanish English GGUF q6 k
Qwen · Agnuxo
Params7.62B
Context128K
Smallest6.3 GB
Tool use
QW
Agente GPT Qwen 2.5 3B GGUF 16bit
Qwen · Agnuxo
Params3.4B
Context32K
Smallest6.8 GB
Tool use
QW
Agente Director Qwen2 7B Instruct CODE Python Spanish English GGUF 4bit
Qwen · Agnuxo
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
TI
Tinytron ORCA 7B TinyLlama Instruct CODE Python extra small quantization GGUF 3bit
Tinytron · Agnuxo
Params6.74B
Context4K
Smallest13.5 GB
Coding
GE
gemma 2 2b instruct python CODE assistant GGUF 4bit
Gemma · Agnuxo
Params2.61B
Context8K
Q4_K_M1.7 GB
Coding
QW
Qwen2 1.5B Instruct MOE Director GGUF 16bit
Qwen · Agnuxo
Params1.54B
Context32K
Smallest3.1 GB
GGUF
QW
Qwen2 1.5B Instruct MOE Director GGUF 8bit
Qwen · Agnuxo
Params1.54B
Context32K
Smallest1.6 GB
GGUF

About Agnuxo on Hugging Face

Agnuxo has published 93 GGUF models that ggufmodels.com tracks, across families such as Qwen, Tinytron and Llama. The most downloaded are CAJAL 4B Merged 16bit, Mamba Codestral 7B v0.1 instruct python coding assistant GGUF 4bit and Phi 3.5 mini instruct python coding assistant GGUF 16bit.

The quants Agnuxo publishes most often are Q8_0 (26), F16 (25), Q4_K_M (23) and BF16 (19). Their Q4_K_M files range from 0.0 to 5.6 GB. Parameter counts run from 4M to 12.2B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has Agnuxo published?

93 models are listed here, mainly from the Qwen, Tinytron and Llama families. The most downloaded is CAJAL 4B Merged 16bit.

Which quants does Agnuxo publish?

The most common are Q8_0 (26 models), F16 (25 models), Q4_K_M (23 models) and BF16 (19 models).

Keep browsing