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.

Most downloadedNewestLargestLongest contextSmallest
HA
Hammer2.0 1.5b
Hammer · Nekuromento
Params1.54B
Context32K
Smallest1.6 GB
Tool use
SE
Serpe 7B Q5 K M
Serpe · Nekuromento
Params7.62B
Context32K
Smallest5.4 GB
GGUF
HA
Hammer2.0 7b
Hammer · Nekuromento
Params7.61B
Context32K
Smallest6.3 GB
Tool use
MI
Mistral Interact
Mistral · Nekuromento
Params7.24B
Context32K
Smallest5.1 GB
GGUF
HA
Hammer2.0 7b
Hammer · Nekuromento
Params7.61B
Context32K
Smallest8.1 GB
Tool use
HA
Hammer 4b
Hammer · Nekuromento
Params3.95B
Context32K
Smallest3.2 GB
Tool use
AT
Athene Codegemma 2 7b It Alpaca v1
Athene · Nekuromento
Params8.54B
Context8K
Smallest6.1 GB
GGUF
LL
llama3 empower functions small v1.1 Q5 K M
Llama · Nekuromento
Params8.03B
Context128K
Smallest5.7 GB
Tool use
LL
llama3 empower functions small v1.1 Q8 0
Llama · Nekuromento
Params8.03B
Context128K
Smallest8.5 GB
Tool use
AT
Athena Codegemma 2 9b
Athena · Nekuromento
Params9.24B
Context8K
Smallest6.6 GB
GGUF
MI
Mistral Interact
Mistral · Nekuromento
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SE
Serpe 7B Q6 K
Serpe · Nekuromento
Params7.62B
Context32K
Smallest6.3 GB
GGUF
SE
Serpe 7B Q8 0
Serpe · Nekuromento
Params7.62B
Context32K
Smallest8.1 GB
GGUF
MI
Mistral Interact
Mistral · Nekuromento
Params7.24B
Context32K
Smallest5.9 GB
GGUF
AT
Athena Codegemma 2 9b
Athena · Nekuromento
Params9.24B
Context8K
Smallest7.6 GB
GGUF

Keep browsing