fkun

freykun

·

AI & ML interests

Personal Use

Recent Activity

upvoted a collection 15 days ago

APEX Quants (GGUF)

new activity 26 days ago

DevQuasar/Qwen.Qwen-AgentWorld-35B-A3B-GGUF:llama.cpp crash: missing tensor 'blk.40.attn_norm.weight' (Incorrect GGUF Metadata)

new activity 26 days ago

gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF:llama.cpp crash: missing tensor 'blk.40.attn_norm.weight' (Incorrect GGUF Metadata)

View all activity

Organizations

None yet

upvoted a collection 15 days ago

APEX Quants (GGUF)

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 42 items • Updated 16 days ago • 127

upvoted a collection over 1 year ago

Gemma 3

All versions of Google's new multimodal models including QAT in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 54 items • Updated 3 days ago • 116