Tarjei Mandt PRO

kernelpool's activity

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

New activity in kernelpool/DeepSeek-V4.1-Flash-MXFP4-GGUF about 19 hours ago

Which llama.cpp fork?

2

#1 opened about 23 hours ago by

mmbela

New activity in kernelpool/Kimi-K3-2bit-UVMAX about 2 months ago

Is 1bit possible?

1

#1 opened about 2 months ago by

darthsider

New activity in mlx-community/Hy3-preview-8bit 2 months ago

It doesn't run in oMLX?

1

#1 opened 2 months ago by

Max3143

New activity in mlx-community/Ouro-2.6B-Thinking-4bit 3 months ago

No MLX support of model type ouro - How to run?

2

#1 opened 3 months ago by

pculebras

New activity in inclusionAI/Ling-2.6-flash 5 months ago

Update modeling_bailing_moe_v2_5.py

👍 1

#6 opened 5 months ago by

kernelpool

New activity in meituan-longcat/LongCat-Next 5 months ago

LongCat-Next does not emit opening tag during tool calling

2

#4 opened 6 months ago by

kernelpool

New activity in mlx-community/Step-3.5-Flash-4bit 7 months ago

Minimum RAM required to run this model

👍 1

2

#1 opened 8 months ago by

Arete7

New activity in mlx-community/Kimi-Linear-48B-A3B-Instruct-8bit 8 months ago

ValueError: Model type kimi_linear not supported.

👀 1

3

#1 opened 11 months ago by

x-polyglot-x

New activity in IQuestLab/IQuest-Coder-V1-40B-Loop-Instruct 8 months ago

Question about K2/V2 cache computation in prefill vs generation

2

#10 opened 9 months ago by

kernelpool

New activity in mlx-community/IQuest-Coder-V1-40B-Instruct-4bit 9 months ago

Not working on my Macbook.

2

#1 opened 9 months ago by

anuedaraanu

New activity in mlx-community/K-EXAONE-236B-A23B-5bit 9 months ago

Does mlx-lm support it?

1

#1 opened 9 months ago by

TOTORONG

New activity in mlx-community/IQuest-Coder-V1-40B-Loop-Instruct-4bit 9 months ago

ERROR:root:Model type iquestloopcoder not supported.

2

#1 opened 9 months ago by

dmikushin

New activity in MiniMaxAI/MiniMax-M2.1 9 months ago

Please make 4 bit dwq mlx quant

2

#1 opened 9 months ago by

Narutoouz

New activity in mlx-community/LLaDA2.0-flash-8bit 9 months ago

Model type llada2_moe not supported

1

#1 opened 9 months ago by

alexchapin

New activity in mlx-community/Kimi-Linear-48B-A3B-Instruct-4bit 10 months ago

Only 4k context window?

➕ 2

2

#1 opened 11 months ago by

do-me

New activity in moonshotai/Kimi-Linear-48B-A3B-Instruct 10 months ago

Need assistance in running on Mac

3

#16 opened 10 months ago by

x-polyglot-x

New activity in mlx-community/LLaDA2.0-mini-preview-4bit 10 months ago

it doesn't work

2

#1 opened 10 months ago by

Jack1992

New activity in mlx-community/MiniMax-M2-4bit 11 months ago

MiniMax-M2-4bit not supported

2

#4 opened 11 months ago by

garryo