GGUF models by Nexesenex
44 GGUF models quantized by Nexesenex on Hugging Face. Sizes run from 1.24B to 94.6B parameters. The longest trained context is 195K tokens.
YI
Cgato Thespis Yi 34b v0.7 iMat
Yi · Nexesenex
Params34.4B
Context195K
Q4_K_M20.7 GB
FB
fblgit UNA 34BeagleSimpleMath 32K v1 iMat
Fblgit · Nexesenex
Params34.4B
Context32K
Q4_K_M20.7 GB
MI
yunconglong Mixtral 7Bx2 MoE 13B DPO iMat
Mistral · Nexesenex
Params12.9B
Context32K
Smallest13.7 GB
LL
chargoddard llama 2 34b uncode iMat
Llama · Nexesenex
Params33.7B
Context16K
Smallest12.5 GB
LL
Llama 3.2 1b Odyssea Escalation 0.0
Llama · Nexesenex
Params1.24B
Context128K
Smallest1.3 GB
LL
Llama 3.2 1b Synwave 0.1
Llama · Nexesenex
Params1.5B
Context128K
Smallest1.2 GB
LA
LaDameBlanche v2 95b iMat CQ
Ladameblanche · Nexesenex
Params94.6B
Context32K
Smallest30.3 GB
LL
Llama 3.2 1b Syneridol 0.2
Llama · Nexesenex
Params1.5B
Context128K
Smallest1.6 GB
LL
Llama_3.2_1b_Odyssea_Escalation_0.0
Llama · Nexesenex
Params1.24B
Context128K
Smallest1.3 GB
AI
Airoboros 33b 3.1.2
Airoboros · Nexesenex
Params32.5B
Context2K
Q4_K_M19.6 GB
YI
Cgato Thespis Yi 34b DPO v0.7 iMat
Yi · Nexesenex
Params34.4B
Context195K
Q4_K_M20.7 GB
LL
Llama 3.2 1b Odyssea Escalation 0.2
Llama · Nexesenex
Params1.5B
Context128K
Smallest1.6 GB
OR
orca mini v9 6 1B Instruct
Orca · Nexesenex
Params1.24B
Context128K
Smallest1.3 GB
LL
Llama 3.2 1b Sydonia 0.1
Llama · Nexesenex
Params1.5B
Context128K
Smallest1.6 GB