IsValorum PRO

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 collection 1 day ago

APEX-I NanoPlus — Standard (MoE)

updated a collection 1 day ago

APEX-I NanoPlus — Standard (MoE)

new activity 1 day ago

IsValorum/MiniPlus-NanoPlus-Requests:Model Requests & Suggestions

View all activity

Organizations

None yet

New activity in IsValorum/MiniPlus-NanoPlus-Requests 1 day ago

Model Requests & Suggestions

#1 opened 24 days ago by

New activity in IsValorum/Tiel-Coder-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF 1 day ago

Reproducable stray artifacts

#3 opened 7 days ago by

New activity in IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF 2 days ago

Model loading error

#2 opened 2 days ago by

Brenchmarks: PPL and ∆PPL vs BF16 situation

#1 opened 8 days ago by

New activity in IsValorum/Qwen3.8-Flash-Coder-APEX-I-MiniPlus-V2.1-GGUF 2 days ago

Hoping for V3 MiniPlus on this Model

#2 opened 3 days ago by

New activity in IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF 2 days ago

Original version

#1 opened 3 days ago by

New activity in IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-NanoPlus-GGUF 2 days ago

Abliterated version

#2 opened 2 days ago by

taureanblock1145

New activity in IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-NanoPlus-V3-GGUF 4 days ago

Fixed: 'blk.64.attn_norm.weight not found' loading error in llama.cpp (How to fix locally without redownloading)

#1 opened 9 days ago by

New activity in IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF 4 days ago

Fixed: 'blk.64.attn_norm.weight not found' loading error in llama.cpp (How to fix locally without redownloading)

#1 opened 9 days ago by

New activity in IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF 6 days ago

Great work — feedback from a 24 GB AMD (Vulkan) user: two reproducible agentic issues + one template suggestion

#3 opened 21 days ago by

New activity in IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF 6 days ago

Erratic uncensorship

#2 opened 8 days ago by

New activity in IsValorum/Huihui-Qwen3.8-27B-Abliterated-VAL-APEX-I-NanoPlus-V3-GGUF 7 days ago

Benchmark Top MiniPlus models

#2 opened 9 days ago by

New activity in IsValorum/KAT-Coder-V2.5-Dev-APEX-I-MiniPlus-V2.1-GGUF 8 days ago

Vision and MTP head please!

#1 opened 8 days ago by

New activity in IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-NanoPlus-GGUF 8 days ago

Brenchmarks: PPL and ∆PPL vs BF16 situation

#1 opened 8 days ago by

New activity in IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF 8 days ago

The original EfficientThink model was upgraded

#2 opened 9 days ago by

New activity in IsValorum/Qwen3.8-27B-VAL-APEX-I-MiniPlus-V3-GGUF 9 days ago

KLD data

#1 opened 9 days ago by

New activity in IsValorum/Huihui-Qwen3.8-27B-Abliterated-VAL-APEX-I-NanoPlus-V3-GGUF 9 days ago

Miracle? And suggestion...

#1 opened 12 days ago by

New activity in IsValorum/Occamy-1.0-APEX-I-NanoPlus-GGUF 11 days ago

Works great but MTP needed

#1 opened 12 days ago by

New activity in IsValorum/Qwen3.8-Flash-Coder-APEX-I-NanoPlus-GGUF 12 days ago

Qwen 3.8 flash for only 18gb ?

#2 opened 15 days ago by

New activity in IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF 13 days ago

Error in chat_template.jinja

#6 opened 13 days ago by