Ben's picture

Open to Work

Ben

D8A

·

AI & ML interests

Innovating with AI since 2013: AI & ML Consultant | Entrepreneur | Architect | Geek | Armchair Philosopher | Experimenter | Catalyst | AI Alignment | Safety Research | R&D

Recent Activity

new activity 22 days ago

dealignai/MiniMax-M2.7-JANGTQ-CRACK:Recently took interest in your models - weight difference? 55GB mentioned vs 60.72GB (actual) ?

new activity about 2 months ago

DontPlanToEnd/UGI-Leaderboard:I will be testing fewer finetunes/merges

new activity about 2 months ago

DontPlanToEnd/UGI-Leaderboard:Eval Request: gpt-oss-120b

View all activity

Organizations

New activity in dealignai/MiniMax-M2.7-JANGTQ-CRACK 22 days ago

Recently took interest in your models - weight difference? 55GB mentioned vs 60.72GB (actual) ?

#1 opened 22 days ago by

New activity in DontPlanToEnd/UGI-Leaderboard about 2 months ago

I will be testing fewer finetunes/merges

#624 opened about 2 months ago by

Eval Request: gpt-oss-120b

#611 opened about 2 months ago by

New activity in mradermacher/model_requests 2 months ago

Please i-quant ArliAI Qwen 3.5 27B Derestricted

#1988 opened 2 months ago by

updated a model 2 months ago

D8A/gemma-3-27b-it-heretic-v1.2-mlx-6Bit

27B • Updated Mar 8 • 19

published a model 2 months ago

D8A/gemma-3-27b-it-heretic-v1.2-mlx-6Bit

27B • Updated Mar 8 • 19

updated a model 2 months ago

D8A/Cydonia-22B-v1.3-mlx-6Bit

22B • Updated Mar 8 • 39

published a model 2 months ago

D8A/Cydonia-22B-v1.3-mlx-6Bit

22B • Updated Mar 8 • 39

updated a model 2 months ago

D8A/gpt-oss-20b-heretic-ara-v3-mlx-8Bit

Text Generation • 21B • Updated Mar 5 • 260

published a model 2 months ago

D8A/gpt-oss-20b-heretic-ara-v3-mlx-8Bit

Text Generation • 21B • Updated Mar 5 • 260

New activity in DontPlanToEnd/UGI-Leaderboard 2 months ago

Test all of the new qwen3.5's

#565 opened 3 months ago by

New activity in mlx-community/mlx-my-repo 7 months ago

Please update to v0.26.0

#56 opened 11 months ago by

New activity in DontPlanToEnd/UGI-Leaderboard 7 months ago

Any news on the awesome new benchmarks?

#373 opened 8 months ago by

updated a model 11 months ago

D8A/Impish_Magic_24B-mlx-6Bit

5B • Updated Jun 20, 2025 • 8

published a model 11 months ago

D8A/Impish_Magic_24B-mlx-6Bit

5B • Updated Jun 20, 2025 • 8

updated a model 11 months ago

D8A/XortronCriminalComputingConfig-mlx-6Bit

Text Generation • 5B • Updated Jun 19, 2025 • 13

published a model 11 months ago

D8A/XortronCriminalComputingConfig-mlx-6Bit

Text Generation • 5B • Updated Jun 19, 2025 • 13

New activity in mlx-community/Qwen3-30B-A3B-4bit-DWQ-05082025 about 1 year ago

Quality vs the day earlier 0508 version?

#2 opened about 1 year ago by

New activity in mlx-community/Qwen3-30B-A3B-4bit-DWQ-0508 about 1 year ago

What distinguishes this model from another MLX-Community/Qwen3-30B-A3B-4bit-DWQ?

#1 opened about 1 year ago by

New activity in KnutJaegersberg/2-bit-LLMs about 2 years ago

Word of thanks and suggestions for more 120B models

#6 opened about 2 years ago by