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
LL
Llama 3.1 WhiteRabbitNeo 2 8B
Llama · Nekuromento
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ST
Codefuse Starcoder2 15b
StarCoder · Nekuromento
Params16B
Context16K
Q4_K_M9.9 GB
Coding
AT
Athene Codegemma 2 7b It Alpaca v1
Athene · Nekuromento
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
AT
Athena Codegemma 2 9b
Athena · Nekuromento
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GH
ghost coder 8b beta 1608 Q6 K
Ghost · Nekuromento
Params8.03B
Context8K
Smallest6.6 GB
CodingTool use
GH
Ghost 8b Beta 1608
Ghost · Nekuromento
Params8.03B
Context8K
Smallest5.7 GB
Tool use
QW
SenecaLLM x Qwen2.5 7B CyberSecurity Q4 K M
Qwen · Nekuromento
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
LI
Lily Cybersecurity 7B v0.2 Q6 K
Lily · Nekuromento
Params7.24B
Context32K
Smallest5.9 GB
GGUF
ST
Codefuse Starcoder2 15b
StarCoder · Nekuromento
Params16B
Context16K
Smallest11.4 GB
Coding
LI
Lily Cybersecurity 7B v0.2 Q4 K M
Lily · Nekuromento
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
HA
Hammer2.0 0.5b
Hammer · Nekuromento
Params494M
Context32K
Smallest0.5 GB
Tool use
HA
Hammer 1.5b
Hammer · Nekuromento
Params1.54B
Context32K
Smallest1.6 GB
Tool use
LI
Lily Cybersecurity 7B v0.2 Q5 K M
Lily · Nekuromento
Params7.24B
Context32K
Smallest5.1 GB
GGUF
HA
Hammer2.1 3b
Hammer · Nekuromento
Params3.09B
Context32K
Smallest2.5 GB
Tool use
HA
Hammer2.1 3b
Hammer · Nekuromento
Params3.09B
Context32K
Smallest3.3 GB
Tool use
WA
Watt Tool 8B
Watt · Nekuromento
Params8.03B
Context128K
Smallest6.6 GB
Tool use
HA
Hammer2.1 0.5b
Hammer · Nekuromento
Params494M
Context32K
Smallest0.5 GB
Tool use
LI
Lily Cybersecurity 7B v0.2 Q8 0
Lily · Nekuromento
Params7.24B
Context32K
Smallest7.7 GB
GGUF
LL
Llama 3.1 WhiteRabbitNeo 2 8B
Llama · Nekuromento
Params8.03B
Context128K
Smallest6.6 GB
GGUF
GH
ghost coder 8b beta 1608 Q4 K M
Ghost · Nekuromento
Params8.03B
Context8K
Q4_K_M4.9 GB
CodingTool use
QW
SenecaLLM x Qwen2.5 7B CyberSecurity Q6 K
Qwen · Nekuromento
Params7.62B
Context32K
Smallest6.3 GB
Tool use
LL
Llama 3.1 WhiteRabbitNeo 2 8B
Llama · Nekuromento
Params8.03B
Context128K
Smallest5.7 GB
GGUF
HA
Hammer2.1 1.5b
Hammer · Nekuromento
Params1.54B
Context32K
Smallest1.6 GB
Tool use
GH
Ghost 8b Beta 1608
Ghost · Nekuromento
Params8.03B
Context8K
Smallest6.6 GB
Tool use
QW
SenecaLLM x Qwen2.5 7B CyberSecurity Q5 K M
Qwen · Nekuromento
Params7.62B
Context32K
Smallest5.4 GB
Tool use
GE
Gemma2 Nephilim v3 9B
Gemma · Nekuromento
Params9.24B
Context8K
Smallest7.6 GB
GGUF
ST
Codefuse Starcoder2 15b
StarCoder · Nekuromento
Params16B
Context16K
Smallest13.1 GB
Coding
FU
functionary v4r small preview Q4 K M
Functionary · Nekuromento
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
HA
Hammer2.1 1.5b
Hammer · Nekuromento
Params1.54B
Context32K
Smallest1.3 GB
Tool use
HA
Hammer2.1 7b
Hammer · Nekuromento
Params7.61B
Context32K
Q4_K_M4.7 GB
Tool use

About Nekuromento on Hugging Face

Nekuromento has published 75 GGUF models that ggufmodels.com tracks, across families such as Hammer, Llama and Ghost. The most downloaded are Llama 3.1 WhiteRabbitNeo 2 8B, Codefuse Starcoder2 15b and Athene Codegemma 2 7b It Alpaca v1.

The quants Nekuromento publishes most often are Q6_K (23), Q5_K_M (20), Q8_0 (16) and Q4_K_M (16). Their Q4_K_M files range from 1.9 to 9.9 GB. Parameter counts run from 494M to 16B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has Nekuromento published?

75 models are listed here, mainly from the Hammer, Llama and Ghost families. The most downloaded is Llama 3.1 WhiteRabbitNeo 2 8B.

Which quants does Nekuromento publish?

The most common are Q6_K (23 models), Q5_K_M (20 models), Q8_0 (16 models) and Q4_K_M (16 models).

Keep browsing