Tom Turney

thetom-ai's activity

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

liked a dataset 4 days ago

AlienKevin/SWE-ZERO-12M-trajectories

Viewer • Updated 4 days ago • 12.3M • 7.08k • 70

New activity in thetom-ai/Qwen3.6-27B-ConfigI-MLX 8 days ago

Fatal error: [metal::Device] Unable to load kernel turbo_dequant_rotated_4_256_bf16. on

2

#2 opened 8 days ago by

heykb

May I ask whether MTP (Multi-Token Prediction) is currently supported in vLLM-swift?

2

#1 opened 8 days ago by

heykb

updated a model 24 days ago

thetom-ai/Qwen3.6-27B-ConfigI-MLX

Text Generation • 27B • Updated 24 days ago • 1.5k • 5

published a model 24 days ago

thetom-ai/Qwen3.6-27B-ConfigI-MLX

Text Generation • 27B • Updated 24 days ago • 1.5k • 5

updated 2 models about 1 month ago

thetom-ai/Qwen3.6-35B-A3B-ConfigI-GGUF

Text Generation • 35B • Updated Apr 17 • 272

thetom-ai/Qwen3.6-35B-A3B-ConfigI-MLX

Text Generation • 35B • Updated Apr 17 • 3.12k • 8

published 2 models about 1 month ago

thetom-ai/Qwen3.6-35B-A3B-ConfigI-GGUF

Text Generation • 35B • Updated Apr 17 • 272

thetom-ai/Qwen3.6-35B-A3B-ConfigI-MLX

Text Generation • 35B • Updated Apr 17 • 3.12k • 8

New activity in thetom-ai/MiniMax-M2.7-ConfigI-MLX about 1 month ago

Awesome Quant - great performance on m4 max

👍 1

2

#1 opened about 1 month ago by

Narutoouz

updated a model about 1 month ago

thetom-ai/Gemma-4-26B-A4B-it-ConfigI-MLX

Text Generation • 25B • Updated Apr 15 • 261 • 1

published a model about 1 month ago

thetom-ai/Gemma-4-26B-A4B-it-ConfigI-MLX

Text Generation • 25B • Updated Apr 15 • 261 • 1

updated a model about 1 month ago

thetom-ai/MiniMax-M2.7-ConfigI-MLX

Text Generation • 229B • Updated Apr 13 • 2.01k • 15

published a model about 1 month ago

thetom-ai/MiniMax-M2.7-ConfigI-MLX

Text Generation • 229B • Updated Apr 13 • 2.01k • 15

updated a collection about 1 month ago

TurboQuant Plus - Models V0.1.0

Collection

A collection of TurboQuant+ compressed models designed to improve quality at practical memory limits. TurboQuant+ applies tensor-aware compression in • 3 items • Updated Apr 8 • 1

updated a model about 1 month ago

thetom-ai/Meta-Llama-3.1-70B-Instruct-TQPlus

Text Generation • Updated Apr 8

published a model about 1 month ago

thetom-ai/Meta-Llama-3.1-70B-Instruct-TQPlus

Text Generation • Updated Apr 8

updated a model about 1 month ago

thetom-ai/Gemma-4-31B-it-TQPlus

Text Generation • 31B • Updated Apr 8 • 112 • 2