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 about 19 hours ago
divinetribe/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-8bit updated a model 2 days ago
divinetribe/yolov8n-oiv7-coreml updated a model 2 days ago
divinetribe/gemma-4-31b-it-abliterated-4bit-mlxOrganizations
None yet
Considerably better than the other abliterated model flying around
3
#1 opened about 2 months ago
by 
wacomctl672
Can we get this with "tool use" available?
12
#1 opened 2 months ago
by 
kolyno25
LM Studio MLX doesn’t support "muse_glimmer"
👍 1
2
#1 opened 2 months ago
by 
atdaniel
MLX 4-bit conversion of gemma-4-12B-it — with vision + audio embedder weights preserved
1
#27 opened 4 months ago
by 
jokernifty
How to get Muse-Glimmer working on a Mac / MacBook Pro in LM Studio and the M5 Metal Tensor issue
1
#42 opened 2 months ago
by 
Portll-LLM
Thank you — seed-vc is doing the voice conversion in a local music app
#2 opened 2 months ago
by divinetribe
generation_config.json eos_token_id is the pad token (151643), causing runaway generation
#6 opened 2 months ago
by divinetribe
Open MLX runtime for the vision + audio towers
1
#1 opened 3 months ago
by divinetribe
Open MLX runtime for the vision + audio towers
1
#1 opened 3 months ago
by divinetribe