GGUF models by logihertzsystems
40 GGUF models quantized by logihertzsystems on Hugging Face. Sizes run from 3.09B to 7.62B parameters. The longest trained context is 125K tokens.
NY
Nyra Main 7B GGUF Q4 K M
Nyra · logihertzsystems
Params7.62B
Context32K
Q4_K_M4.7 GB
NY
Nyra Main 7B GGUF Q8 0
Nyra · logihertzsystems
Params7.62B
Context32K
Smallest8.1 GB
NY
Nyra Vision 3B GGUF IQ1 M
Nyra · logihertzsystems
Params3.09B
Context125K
Smallest0.9 GB
NY
Nyra Vision 3B GGUF IQ1 S
Nyra · logihertzsystems
Params3.09B
Context125K
Smallest0.8 GB
NY
Nyra Vision 3B GGUF Q4 K M
Nyra · logihertzsystems
Params3.09B
Context125K
Q4_K_M1.9 GB
NY
Nyra Vision 3B GGUF Q8 0
Nyra · logihertzsystems
Params3.09B
Context125K
Smallest3.3 GB
NY
Nyra Vision 7B GGUF IQ1 M
Nyra · logihertzsystems
Params7.62B
Context32K
Smallest2.0 GB
NY
Nyra Vision 7B GGUF IQ1 S
Nyra · logihertzsystems
Params7.62B
Context125K
Smallest1.9 GB
NY
Nyra Vision 7B GGUF Q4 K M
Nyra · logihertzsystems
Params7.62B
Context32K
Q4_K_M4.7 GB
NY
Nyra Vision 7B GGUF Q8 0
Nyra · logihertzsystems
Params7.62B
Context32K
Smallest8.1 GB