Raullen's picture

Raullen

Raullen

·

AI & ML interests

None yet

Recent Activity

new activity 2 days ago

allenai/tmax-9b:MLX quantizations + M3 Ultra benchmark (107 tok/s on 4-bit)

updated a model 2 days ago

mlx-community/Tmax-27B-MLX-4bit

updated a model 2 days ago

mlx-community/Tmax-27B-MLX-6bit

View all activity

Organizations

New activity in allenai/tmax-9b 2 days ago

MLX quantizations + M3 Ultra benchmark (107 tok/s on 4-bit)

#2 opened 2 days ago by

New activity in google/gemma-4-12B-it 8 days ago

gemma-4-12B-it: deterministic "thought\n thought\n …" degenerate loop on long agent prompts (~60% reproducer, 4-bit, repros across temperatures)

#41 opened 8 days ago by

New activity in mlx-community/DeepSeek-V4-Flash-8bit about 2 months ago

Bundled chat_template.jinja is chat-only — strips tools silently

#1 opened about 2 months ago by

New activity in deepseek-ai/DeepSeek-V4-Flash about 2 months ago

Add chat template

#16 opened 2 months ago by

New activity in deepseek-ai/DeepSeek-V3 2 months ago

Built a free hosted demo of V3 — feedback welcome

#121 opened 2 months ago by

New activity in Jackrong/Qwopus3.5-27B-v3 3 months ago

Benchmarked on Apple Silicon (M3 Ultra) — 39 tok/s, 100% tool calling via Rapid-MLX

#19 opened 3 months ago by