👋 Open to Work

Maximilian Weigt

Manuun1

·

https://www.maximilianweigt.com

manuun1

AI & ML interests

Open Weight Models for coding, ai-ops, and building automation workflows mostly for regulated governmental use cases.

Organizations

New activity in Qwen/Qwen3.8-27B 3 months ago

DFlash draft model instead of MTP one

#54 opened 3 months ago by

New activity in ornith-ai/Ornith-1.0-397B 4 months ago

where is 31B-Dense?

#7 opened 5 months ago by

New activity in unsloth/GLM-5.2-GGUF 5 months ago

Getting MTP working?

#7 opened 5 months ago by

New activity in unsloth/MiMo-V2.5-GGUF 5 months ago

MTP Supported?

#3 opened 5 months ago by

New activity in Qwen/Qwen3.6-27B 7 months ago

MTP Speculative Decoding absolutely no performance gains

#17 opened 7 months ago by

New activity in Qwen/Qwen3.6-35B-A3B 7 months ago

Thanks for contributing to the OpenWeight Community

#8 opened 7 months ago by

New activity in unsloth/MiniMax-M2.7-GGUF 7 months ago

Comparison of different Quants?

#3 opened 7 months ago by

Dynamic Quants producing garbage thinking output (llama.cpp + Cuda 13 issue)

#1 opened 7 months ago by

New activity in MiniMaxAI/MiniMax-M2.5 7 months ago

Minimax 2.7???

#53 opened 8 months ago by

New activity in MiniMaxAI/MiniMax-M2.5 9 months ago

Recommended max_kv_size for MLX deployment to prevent OOM on Apple Silicon

#14 opened 9 months ago by