The doctor is in
Gheorghe Chesler
nightmedia
AI & ML interests
Quanting destroys quality. What if it improves it?
I am exploring creative ways to reach a size/quality compromise that also improve the average performance byte per byte. Focusing the model.
Recent Activity
updated
a model
about 1 hour ago
nightmedia/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-q8-mlx
updated
a model
about 1 hour ago
nightmedia/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-q8-ml
published
a model
about 4 hours ago
nightmedia/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-q8-mlx
Organizations
None yet
models
63
nightmedia/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-q8-mlx
Text Generation
•
18B
•
Updated
nightmedia/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-q8-ml
Text Generation
•
17B
•
Updated
nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-12B-64k-mlx
Text Generation
•
12B
•
Updated
•
1
nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-12B-64k-dwq6-mlx
Text Generation
•
12B
•
Updated
•
1
nightmedia/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-q8-mlx
Text Generation
•
42B
•
Updated
•
1
nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-12B-128k-mlx
Text Generation
•
12B
•
Updated
•
2
nightmedia/Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B-q8-mlx
Text Generation
•
53B
•
Updated
•
4
nightmedia/Qwen2.5-8x7B-Vee-Eight-Coder-Instruct-53B-q6-mlx
Text Generation
•
53B
•
Updated
•
13
nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-12B-q8-mlx
Updated
nightmedia/Qwen2.5-6x7B-Six-Pack-Coder-Instruct-42B-q6-mlx
Text Generation
•
42B
•
Updated
•
10
datasets
0
None public yet