matt macosko
divinetribe
AI & ML interests
local inference, apple silicon, mlx, quantization, llama, gemma, robotics, computer vision, yolov8, coreml, voice cloning, autonomous agents
Recent Activity
updated a model 6 days ago
divinetribe/Nemotron-3-Nano-Omni-30B-Abliterated-MM-bf16 updated a model 9 days ago
divinetribe/Nemotron-3-Nano-Omni-30B-Abliterated-MM-8bitOrganizations
None yet
Considerably better than the other abliterated model flying around
3
#1 opened 7 days ago
by 
wacomctl672
Can we get this with "tool use" available?
12
#1 opened 21 days ago
by 
kolyno25
The vision tower is missing
1
#1 opened 5 months ago
by 
Regicardano
LM Studio MLX doesn’t support "muse_glimmer"
👍 1
2
#1 opened 22 days ago
by 
atdaniel
MLX 4-bit conversion of gemma-4-12B-it — with vision + audio embedder weights preserved
1
#27 opened 3 months ago
by 
jokernifty
Thank you — seed-vc is doing the voice conversion in a local music app
#2 opened 25 days ago
by divinetribe
generation_config.json eos_token_id is the pad token (151643), causing runaway generation
#6 opened 28 days ago
by divinetribe
Open MLX runtime for the vision + audio towers
1
#1 opened about 2 months ago
by divinetribe
Open MLX runtime for the vision + audio towers
1
#1 opened about 2 months ago
by divinetribe