Maximilian Weigt
Manuun1
·
AI & ML interests
Open Weight Models for coding, ai-ops, and building automation workflows mostly for regulated governmental use cases.
Recent Activity
new activity 32 minutes ago
unsloth/MiMo-V2.5-GGUF:MTP Supported? new activity about 2 months ago
Qwen/Qwen3.6-27B:MTP Speculative Decoding absolutely no performance gains new activity 2 months ago
Qwen/Qwen3.6-35B-A3B:Thanks for contributing to the OpenWeight CommunityOrganizations
MTP Supported?
1
#3 opened 5 days ago
by 
alexanderacuna
MTP Speculative Decoding absolutely no performance gains
#17 opened about 2 months ago
by Manuun1
Thanks for contributing to the OpenWeight Community
👍 2
#8 opened 2 months ago
by Manuun1
Comparison of different Quants?
👍 2
12
#3 opened 2 months ago
by Manuun1
Dynamic Quants producing garbage thinking output (llama.cpp + Cuda 13 issue)
👍 1
20
#1 opened 2 months ago
by 
orlandocollins
Minimax 2.7???
49
#53 opened 3 months ago
by 
rombodawg
Recommended max_kv_size for MLX deployment to prevent OOM on Apple Silicon
👍 2
1
#14 opened 4 months ago
by 
Neo2025new