Native MLX APEX Abliterated releases using IsValorum's mixed-precision recipes for Apple Silicon.
IsValorum
IsValorum
AI & ML interests
I'm tired of generic quantizations that consume too many resources when they could be even higher quality and consume much less, but nobody was doing it then I thought Why don't I do it myself? And here I am, the first person to dedicate everything to quality over quantity.
Recent Activity
updated a model about 2 hours ago
IsValorum/Xing4.0-29B-A4B-APEX-I-NanoPlus-Abliterated-GGUF updated a model about 2 hours ago
IsValorum/Xing4.0-29B-A4B-APEX-I-MiniPlus-V2.1-Abliterated-GGUF updated a model about 2 hours ago
IsValorum/XYZ-Aquila-mini-APEX-I-MiniPlus-V2.1-GGUFOrganizations
None yet
Official collection of Abliterated / Uncensored APEX-I-MiniPlus models.
-
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2.1-Abliterated-GGUF
Text Generation • 35B • Updated • 5.49k • 9 -
IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF
Text Generation • 35B • Updated • 33.6k • 25 -
IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF
Image-Text-to-Text • 35B • Updated • 8.22k • 4 -
IsValorum/Cyber-Tiel-Coder-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF
Image-Text-to-Text • 35B • Updated • 3.22k • 5
Historical legacy collection of APEX-I-MiniPlus V2 quantization releases.
-
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 35B • Updated • 8.19k • 7 -
IsValorum/Apodex-1.1-mini-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 36B • Updated • 3.19k -
IsValorum/KAT-Coder-V2.5-Dev-APEX-I-MiniPlus-V2-GGUF
Text Generation • 35B • Updated • 2.82k • 1 -
IsValorum/Thomson-1.0-Small-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 35B • Updated • 2.75k
Handcrafted APEX-I GGUFs optimized for 4GB-24GB VRAM setups with high throughput.
-
IsValorum/Iris-mini-APEX-I-MiniPlus-V1-GGUF
Text Generation • 36B • Updated • 3.58k • 2 -
IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF
Image-Text-to-Text • 35B • Updated • 4.14k • 3 -
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 35B • Updated • 8.19k • 7 -
IsValorum/Apodex-1.1-mini-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 36B • Updated • 3.19k
Architectural quantization line targeting 12-13 GB with solid Q4 quality and fast RAM streaming on 16GB VRAM.
-
IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-NanoPlus-GGUF
Image-Text-to-Text • 36B • Updated • 2.21k • 2 -
IsValorum/Occamy-1.0-APEX-I-NanoPlus-GGUF
Image-Text-to-Text • 35B • Updated • 1.62k • 3 -
IsValorum/Ornith-1.5-35B-A3B-APEX-I-NanoPlus-GGUF
Image-Text-to-Text • 35B • Updated • 1.86k • 1 -
IsValorum/Tiel-Coder-35B-A3B-APEX-I-NanoPlus-GGUF
Image-Text-to-Text • 35B • Updated • 2.15k • 6
Definitive frontier V2.1 specification within the 13-14 GB envelope with zero AVX2 stalls.
-
IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-GGUF
Text Generation • 35B • Updated • 11.3k • 15 -
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2.1-GGUF
Text Generation • 35B • Updated • 5.37k • 13 -
IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF
Text Generation • 35B • Updated • 8.04k • 3 -
IsValorum/KAT-Coder-V2.5-Dev-APEX-I-MiniPlus-V2.1-GGUF
Text Generation • 35B • Updated • 3.87k • 3
Historical legacy collection of early APEX-I-MiniPlus V1 quantization releases.
Native MLX APEX Abliterated releases using IsValorum's mixed-precision recipes for Apple Silicon.
Architectural quantization line targeting 12-13 GB with solid Q4 quality and fast RAM streaming on 16GB VRAM.
-
IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-NanoPlus-GGUF
Image-Text-to-Text • 36B • Updated • 2.21k • 2 -
IsValorum/Occamy-1.0-APEX-I-NanoPlus-GGUF
Image-Text-to-Text • 35B • Updated • 1.62k • 3 -
IsValorum/Ornith-1.5-35B-A3B-APEX-I-NanoPlus-GGUF
Image-Text-to-Text • 35B • Updated • 1.86k • 1 -
IsValorum/Tiel-Coder-35B-A3B-APEX-I-NanoPlus-GGUF
Image-Text-to-Text • 35B • Updated • 2.15k • 6
Official collection of Abliterated / Uncensored APEX-I-MiniPlus models.
-
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2.1-Abliterated-GGUF
Text Generation • 35B • Updated • 5.49k • 9 -
IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF
Text Generation • 35B • Updated • 33.6k • 25 -
IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF
Image-Text-to-Text • 35B • Updated • 8.22k • 4 -
IsValorum/Cyber-Tiel-Coder-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF
Image-Text-to-Text • 35B • Updated • 3.22k • 5
Definitive frontier V2.1 specification within the 13-14 GB envelope with zero AVX2 stalls.
-
IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-GGUF
Text Generation • 35B • Updated • 11.3k • 15 -
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2.1-GGUF
Text Generation • 35B • Updated • 5.37k • 13 -
IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF
Text Generation • 35B • Updated • 8.04k • 3 -
IsValorum/KAT-Coder-V2.5-Dev-APEX-I-MiniPlus-V2.1-GGUF
Text Generation • 35B • Updated • 3.87k • 3
Historical legacy collection of APEX-I-MiniPlus V2 quantization releases.
-
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 35B • Updated • 8.19k • 7 -
IsValorum/Apodex-1.1-mini-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 36B • Updated • 3.19k -
IsValorum/KAT-Coder-V2.5-Dev-APEX-I-MiniPlus-V2-GGUF
Text Generation • 35B • Updated • 2.82k • 1 -
IsValorum/Thomson-1.0-Small-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 35B • Updated • 2.75k
Historical legacy collection of early APEX-I-MiniPlus V1 quantization releases.
Handcrafted APEX-I GGUFs optimized for 4GB-24GB VRAM setups with high throughput.
-
IsValorum/Iris-mini-APEX-I-MiniPlus-V1-GGUF
Text Generation • 36B • Updated • 3.58k • 2 -
IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF
Image-Text-to-Text • 35B • Updated • 4.14k • 3 -
IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 35B • Updated • 8.19k • 7 -
IsValorum/Apodex-1.1-mini-APEX-I-MiniPlus-V2-GGUF
Image-Text-to-Text • 36B • Updated • 3.19k