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

new activity 1 day ago

NousResearch/Hermes-4-14B:generation_config.json eos_token_id is the pad token (151643), causing runaway generation

updated a model 1 day ago

divinetribe/Hermes-4-14B-abliterated-4bit-mlx

new activity 20 days ago

mlx-community/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-4bit:Open MLX runtime for the vision + audio towers

View all activity

Organizations

None yet

New activity in NousResearch/Hermes-4-14B 1 day ago

generation_config.json eos_token_id is the pad token (151643), causing runaway generation

#6 opened 1 day ago by

divinetribe

updated a model 1 day ago

divinetribe/Hermes-4-14B-abliterated-4bit-mlx

Text Generation • 2B • Updated 1 day ago • 518

New activity in mlx-community/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-4bit 20 days ago

Open MLX runtime for the vision + audio towers

#1 opened 20 days ago by

divinetribe

updated a model about 1 month ago

divinetribe/Huihui-Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-abliterated-4bit-mlx

80B • Updated Jun 23 • 57 • 1

published a model about 2 months ago

divinetribe/Huihui-Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-abliterated-4bit-mlx

80B • Updated Jun 23 • 57 • 1

updated a model about 2 months ago

divinetribe/Huihui-gemma-4-31B-it-abliterated-4bit-mlx

Text Generation • 31B • Updated Jun 16 • 194

published a model about 2 months ago

divinetribe/Huihui-gemma-4-31B-it-abliterated-4bit-mlx

Text Generation • 31B • Updated Jun 16 • 194

updated a model about 2 months ago

divinetribe/Huihui-Qwen3-8B-abliterated-v2-4bit-mlx

Text Generation • 1B • Updated Jun 15 • 63

published a model about 2 months ago

divinetribe/Huihui-Qwen3-8B-abliterated-v2-4bit-mlx

Text Generation • 1B • Updated Jun 15 • 63

updated a model 2 months ago

divinetribe/gemma-4-12B-it-abliterated-4bit-mlx-text

Text Generation • 3B • Updated Jun 5 • 111

published a model 2 months ago

divinetribe/gemma-4-12B-it-abliterated-4bit-mlx-text

Text Generation • 3B • Updated Jun 5 • 111

updated a collection 2 months ago

Abliterated MLX for Apple Silicon

Collection

Uncensored (abliterated) language models converted to MLX 4-bit for Apple Silicon — local, fast, no cloud. Companion to the claude-code-local project. • 6 items • Updated Jun 5

updated a model 2 months ago

divinetribe/Qwen3.6-27B-abliterated-4bit-mlx

Text Generation • 27B • Updated Jun 5 • 110

published a model 2 months ago

divinetribe/Qwen3.6-27B-abliterated-4bit-mlx

Text Generation • 27B • Updated Jun 5 • 110

updated a collection 2 months ago

Abliterated MLX for Apple Silicon

Collection

Uncensored (abliterated) language models converted to MLX 4-bit for Apple Silicon — local, fast, no cloud. Companion to the claude-code-local project. • 6 items • Updated Jun 5

updated a model 2 months ago

divinetribe/gemma-4-12B-it-abliterated-4bit-mlx

Text Generation • 3B • Updated Jun 5 • 57

matt macosko

AI & ML interests

Recent Activity

Organizations

divinetribe's activity

generation_config.json eos_token_id is the pad token (151643), causing runaway generation

Open MLX runtime for the vision + audio towers