Nexes the Elder
Nexesenex
AI & ML interests
Maintaining KoboldCPP fork Croco.Cpp, and Lllama.cpp fork NXS_Llama.cpp
Merging models sometimes.
Making quants of my merges and fav models, often specific to IKL/NXSL/Croco.Cpp.
Barking at many trees.
Thanks to Mradermacher and Bartowski for their imatrixes, I'm using them extensively.
Note : Don't make quants of my merges until they are versioned! (Vx or Vx.x)
Recent Activity
liked
a model
12 days ago
zerofata/GLM-4.5-Iceblink-v2-106B-A12B
new activity
12 days ago
zerofata/GLM-4.5-Iceblink-v2-106B-A12B:Good stuff!
published
a model
19 days ago
Nexesenex/DeepSeek-V2-Lite-Chat-Uncensored-Unbiased-Reasoner-Q8_0-GGUF
Organizations
Legacy L3 70b models merged with Llama 3.1 70b Tess 3 (credit: Miguel Tissera) for 128K context capability and low perplexity.
-
Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
Text Generation • 71B • Updated • 9 -
Nexesenex/Llama_3.x_70b_Tess_Dolphin_128K_v1.2
Text Generation • 71B • Updated • 12 • 1 -
Nexesenex/Llama_3.x_70b_Tess_Cat_128K_v1.0
Text Generation • 71B • Updated • 6 -
Nexesenex/Llama_3.x_70b_L3.3_Athene_128K_v1.02
Text Generation • 71B • Updated • 8 • 1
How I select models ? First, I bench them, to trim the overfit & dumbified models. Then, I test them. The smartest to my taste end-up here.
-
NexesQuants/alchemonaut_QuartetAnemoi-70B-iMat.GGUF
69B • Updated • 324 • 11 -
NexesQuants/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF
69B • Updated • 3.1k • 70 -
NexesQuants/TeeZee_Kyllene-Yi-34B-v1.1-iMat.GGUF
34B • Updated • 2.94k • 27 -
Nexesenex/TomGrc_FusionNet_7Bx2_MoE_v0.1-iMat.GGUF
13B • Updated • 102 • 2
My merges worthy of being downloaded and used.
-
Nexesenex/Llama_3.x_70b_Hexagon_Blue_V1
Text Generation • 71B • Updated • 15 • 1 -
Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat
Text Generation • 71B • Updated • 13 -
Nexesenex/Llama_3.x_70b_Hexagon_Pink_V1
Text Generation • 71B • Updated • 7 • 1 -
Nexesenex/Llama_3.x_70b_Hexagon_Purple_V2
Text Generation • 71B • Updated • 19 • 2
With particular features..
My merges worthy of being downloaded and used.
-
Nexesenex/Llama_3.x_70b_Hexagon_Blue_V1
Text Generation • 71B • Updated • 15 • 1 -
Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat
Text Generation • 71B • Updated • 13 -
Nexesenex/Llama_3.x_70b_Hexagon_Pink_V1
Text Generation • 71B • Updated • 7 • 1 -
Nexesenex/Llama_3.x_70b_Hexagon_Purple_V2
Text Generation • 71B • Updated • 19 • 2
Legacy L3 70b models merged with Llama 3.1 70b Tess 3 (credit: Miguel Tissera) for 128K context capability and low perplexity.
-
Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
Text Generation • 71B • Updated • 9 -
Nexesenex/Llama_3.x_70b_Tess_Dolphin_128K_v1.2
Text Generation • 71B • Updated • 12 • 1 -
Nexesenex/Llama_3.x_70b_Tess_Cat_128K_v1.0
Text Generation • 71B • Updated • 6 -
Nexesenex/Llama_3.x_70b_L3.3_Athene_128K_v1.02
Text Generation • 71B • Updated • 8 • 1
With particular features..
How I select models ? First, I bench them, to trim the overfit & dumbified models. Then, I test them. The smartest to my taste end-up here.
-
NexesQuants/alchemonaut_QuartetAnemoi-70B-iMat.GGUF
69B • Updated • 324 • 11 -
NexesQuants/MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF
69B • Updated • 3.1k • 70 -
NexesQuants/TeeZee_Kyllene-Yi-34B-v1.1-iMat.GGUF
34B • Updated • 2.94k • 27 -
Nexesenex/TomGrc_FusionNet_7Bx2_MoE_v0.1-iMat.GGUF
13B • Updated • 102 • 2