Philip John Basile PRO

philipjohnbasile's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 models about 3 hours ago

philipjohnbasile/DeepSeek-V4-Flash-0731-MLX-M5Max-TargetOnly

Text Generation • 29B • Updated about 2 hours ago • 1

philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX

Text Generation • 6B • Updated about 3 hours ago • 1

published a model about 3 hours ago

philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX

Text Generation • 6B • Updated about 3 hours ago • 1

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-bf16 about 3 hours ago

Source for 711

20

#1 opened 16 days ago by

nightmedia

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-6bit about 7 hours ago

You posted some raw TG numbers with/without MTP - do you happen to have TG/PP at higher contexts?

10

#1 opened 16 days ago by

veldierin

updated a model about 7 hours ago

philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-6bit

Image-Text-to-Text • 6B • Updated about 7 hours ago • 1.88k • 5

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-bf16 about 7 hours ago

The model works on a TPU (v5e-8) in vLLM.

1

#2 opened 3 days ago by

zook-data

liked a model about 9 hours ago

philipjohnbasile/DeepSeek-V4-Flash-0731-MLX-M5Max-TargetOnly

Text Generation • 29B • Updated about 2 hours ago • 1

published a model about 10 hours ago

philipjohnbasile/DeepSeek-V4-Flash-0731-MLX-M5Max-TargetOnly

Text Generation • 29B • Updated about 2 hours ago • 1

New activity in multimodalart/minimax-h3 3 days ago

I make the video and then the page reloads

1

#8 opened 3 days ago by

philipjohnbasile

updated a model 9 days ago

philipjohnbasile/wisp-coder-110m

Text Generation • 0.1B • Updated 8 days ago • 80 • 1

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-ReducedRefusal-MTPLX-6bit 10 days ago

Would it be worthwhile to provide links in the README.md to some of the source discussions/models?

3

#1 opened 11 days ago by

veldierin

updated a model 10 days ago

philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-ReducedRefusal-MTPLX-6bit

Text Generation • 27B • Updated 10 days ago • 584 • 3

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 12 days ago

VERSION: MLX / Apple Silicon conversions (working MTP + vision), plus a reconstructed bf16

11

#31 opened 18 days ago by

philipjohnbasile

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-8bit 12 days ago

Testing GGUF vs MTPLX on Mac m1 Max 64GB

1

#1 opened 13 days ago by

EternalMoonshine

published a model 12 days ago

philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-ReducedRefusal-MTPLX-6bit

Text Generation • 27B • Updated 10 days ago • 584 • 3

updated 2 models 13 days ago

philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-8bit

Image-Text-to-Text • 27B • Updated 12 days ago • 4.01k • 16

philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-4bit

Image-Text-to-Text • 27B • Updated 12 days ago • 2.15k • 4

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 16 days ago

Abliteration not working

👍 3

63

#13 opened 22 days ago by

Dhrhciebcy

liked a model 16 days ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 16 days ago • 1.57M • • 10.5k