Anthony A

anthonyya

1 10

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

z-lab/Qwen3.8-27B-DFlash2

liked a model 3 days ago

z-lab/Qwen3.8-27B-DFlash2-GGUF

liked a model 8 days ago

MiniMaxAI/MiniMax-Music3

View all activity

Organizations

None yet

liked 2 models 3 days ago

z-lab/Qwen3.8-27B-DFlash2

Text Generation • 2B • Updated 2 days ago • 21.1k • 162

z-lab/Qwen3.8-27B-DFlash2-GGUF

Text Generation • 2B • Updated 3 days ago • 15.9k • 67

liked 2 models 8 days ago

MiniMaxAI/MiniMax-Music3

Text-to-Audio • 2B • Updated 7 days ago • 15.7k • 1.14k

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 7 days ago • 1.73M • • 11.8k

liked a model 11 days ago

froggeric/Qwen-Fixed-Chat-Templates

Updated about 6 hours ago • 1.35k

commented on Block Diffusion on Apple Silicon with 3.7× Speedup for Qwopus 3.6 27B 19 days ago

Ignore my previous comment as I was testing the configuration on llama.cpp, which isn't as optimized as MLX based frameworks. However after trying this on mlx-vlm, I'm actually curious how you got this running long enough for your sanity testing. I tried to test it myself, and mlx-vlm is currently suffering from intense RAM spikes (4x the usage) which then very quickly causes OOMs. I opened an issue and I am working with collaborators who confirmed this is an issue.

liked a model 19 days ago

lemuralabs/Qwen3.6-27B-V2-abliterated-uncensored-6-bit-mlx

Image-Text-to-Text • 6B • Updated 16 days ago • 1.52k • 2

updated a model 19 days ago

anthonyya/Qwen3.6-27B-DFlash-8bit

Text Generation • 0.5B • Updated 19 days ago • 256

published a model 19 days ago

anthonyya/Qwen3.6-27B-DFlash-8bit

Text Generation • 0.5B • Updated 19 days ago • 256

updated a model 19 days ago

anthonyya/Qwen3.6-27B-DFlash-4bit

Text Generation • 0.3B • Updated 19 days ago • 284

published a model 19 days ago

anthonyya/Qwen3.6-27B-DFlash-4bit

Text Generation • 0.3B • Updated 19 days ago • 284

updated a model 19 days ago

anthonyya/Qwen3.6-27B-DFlash-6bit

Text Generation • 0.4B • Updated 19 days ago • 100

published a model 19 days ago

anthonyya/Qwen3.6-27B-DFlash-6bit

Text Generation • 0.4B • Updated 19 days ago • 100

New activity in Alittlehammmer/Qwen3.6-27B-DFlash-GGUF-llama.cpp 20 days ago

Are quants required to match?

#1 opened 20 days ago by

anthonyya

commented on Block Diffusion on Apple Silicon with 3.7× Speedup for Qwopus 3.6 27B 20 days ago

Can you run this on a real benchmark? I tested this on my M4 Max with a real coding benchmark and I'm not seeing anything close to your 55 tok/s, I'm getting around 20.