GGUF models by Nekuromento
75 GGUF models quantized by Nekuromento on Hugging Face. Sizes run from 494M to 16B parameters. The longest trained context is 128K tokens.
HA
Hammer2.0 1.5b
Hammer · Nekuromento
Params1.54B
Context32K
Smallest1.6 GB
SE
Serpe 7B Q5 K M
Serpe · Nekuromento
Params7.62B
Context32K
Smallest5.4 GB
HA
Hammer2.0 7b
Hammer · Nekuromento
Params7.61B
Context32K
Smallest6.3 GB
MI
Mistral Interact
Mistral · Nekuromento
Params7.24B
Context32K
Smallest5.1 GB
HA
Hammer2.0 7b
Hammer · Nekuromento
Params7.61B
Context32K
Smallest8.1 GB
HA
Hammer 4b
Hammer · Nekuromento
Params3.95B
Context32K
Smallest3.2 GB
AT
Athene Codegemma 2 7b It Alpaca v1
Athene · Nekuromento
Params8.54B
Context8K
Smallest6.1 GB
LL
llama3 empower functions small v1.1 Q5 K M
Llama · Nekuromento
Params8.03B
Context128K
Smallest5.7 GB
LL
llama3 empower functions small v1.1 Q8 0
Llama · Nekuromento
Params8.03B
Context128K
Smallest8.5 GB
AT
Athena Codegemma 2 9b
Athena · Nekuromento
Params9.24B
Context8K
Smallest6.6 GB
MI
Mistral Interact
Mistral · Nekuromento
Params7.24B
Context32K
Q4_K_M4.4 GB
SE
Serpe 7B Q6 K
Serpe · Nekuromento
Params7.62B
Context32K
Smallest6.3 GB
SE
Serpe 7B Q8 0
Serpe · Nekuromento
Params7.62B
Context32K
Smallest8.1 GB
MI
Mistral Interact
Mistral · Nekuromento
Params7.24B
Context32K
Smallest5.9 GB
AT
Athena Codegemma 2 9b
Athena · Nekuromento
Params9.24B
Context8K
Smallest7.6 GB