Tocchi H PRO

tocchitocchi

AI & ML interests

None yet

Organizations

None yet

Articles 1

Article

Why One Bug Fix Made My Model the Most Downloaded Japanese LLM in MLX Format

models 17

tocchitocchi/NVIDIA-Nemotron-Nano-9B-v2-Japanese-fp16-mlx

9B • Updated Apr 21 • 84

tocchitocchi/NVIDIA-Nemotron-Nano-9B-v2-Japanese-8bit-mlx

9B • Updated Apr 17 • 45

tocchitocchi/NVIDIA-Nemotron-Nano-9B-v2-Japanese-4bit-mlx

1B • Updated Apr 17 • 38

tocchitocchi/GPT-OSS-Swallow-120B-RL-v0.1-6bit-mlx

Text Generation • 26B • Updated Mar 9 • 144 • 1

tocchitocchi/GPT-OSS-Swallow-20B-RL-v0.1-fp16-mlx

Text Generation • 21B • Updated Mar 9 • 60

tocchitocchi/GPT-OSS-Swallow-20B-RL-v0.1-8bit-mlx

Text Generation • 21B • Updated Mar 9 • 42

tocchitocchi/GPT-OSS-Swallow-20B-RL-v0.1-6bit-mlx

Text Generation • 21B • Updated Mar 9 • 132 • 1

tocchitocchi/Qwen3-Swallow-32B-RL-v0.2-MLX-fp16

Text Generation • 33B • Updated Mar 6 • 38 •

tocchitocchi/Qwen3-Swallow-32B-RL-v0.2-MLX-8bit

Text Generation • 33B • Updated Mar 6 • 50

tocchitocchi/Qwen3-Swallow-32B-RL-v0.2-MLX-4bit

Text Generation • 33B • Updated Mar 6 • 89

datasets 0

None public yet