Rewritten Jinja templates fixing 5 bugs in official Qwen 3.5/3.6. Works in LM Studio, llama.cpp, MLX, vLLM.
froggeric
froggeric
AI & ML interests
None yet
Recent Activity
new activity about 20 hours ago
froggeric/Qwen-Fixed-Chat-Templates:v13 to v15 are completely broken in VLLM for qwen3_coder parser new activity about 20 hours ago
froggeric/Qwen-Fixed-Chat-Templates:v15 released with fixes for overthinking/indecision and loops on tool errors new activity 1 day ago
froggeric/Qwen-Fixed-Chat-Templates:v11/v12 performance considerations with Claude Code?Organizations
MLX conversions of Qwen 3.6 with fixed chat templates, vision fixes, and thinking toggle. 4/6/8-bit.
-
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-8bit
Image-Text-to-Text • 8B • Updated • 1.7k -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-6bit
Image-Text-to-Text • 6B • Updated • 1.37k -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
Image-Text-to-Text • 5B • Updated • 3.34k • 3 -
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bit
Image-Text-to-Text • 10B • Updated • 2.64k • 3
Rewritten Jinja templates fixing 5 bugs in official Qwen 3.5/3.6. Works in LM Studio, llama.cpp, MLX, vLLM.
MLX conversions of Qwen 3.6 with fixed chat templates, vision fixes, and thinking toggle. 4/6/8-bit.
-
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-8bit
Image-Text-to-Text • 8B • Updated • 1.7k -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-6bit
Image-Text-to-Text • 6B • Updated • 1.37k -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
Image-Text-to-Text • 5B • Updated • 3.34k • 3 -
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bit
Image-Text-to-Text • 10B • Updated • 2.64k • 3