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 6 hours ago
froggeric/Qwen-Fixed-Chat-Templates:inference throughput drops by 80% with this template updated a model 5 days ago
froggeric/Qwen3.6-27B-MTP-GGUF new activity 7 days ago
froggeric/Qwen-Fixed-Chat-Templates:v19 released with major improvementsOrganizations
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 • 2.05k -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-6bit
Image-Text-to-Text • 6B • Updated • 1.72k • 1 -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
Image-Text-to-Text • 5B • Updated • 4.6k • 3 -
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bit
Image-Text-to-Text • 10B • Updated • 3.6k • 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 • 2.05k -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-6bit
Image-Text-to-Text • 6B • Updated • 1.72k • 1 -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
Image-Text-to-Text • 5B • Updated • 4.6k • 3 -
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bit
Image-Text-to-Text • 10B • Updated • 3.6k • 3
models 17
froggeric/Qwen3.6-27B-MTP-GGUF
Image-Text-to-Text • 27B • Updated • 87.1k • 66
froggeric/Qwen-Fixed-Chat-Templates
Updated • 404
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit
Image-Text-to-Text • 6B • Updated • 5.31k • 4
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-6bit
Image-Text-to-Text • 8B • Updated • 2.63k • 1
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bit
Image-Text-to-Text • 10B • Updated • 3.6k • 3
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
Image-Text-to-Text • 5B • Updated • 4.6k • 3
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-6bit
Image-Text-to-Text • 6B • Updated • 1.72k • 1
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-8bit
Image-Text-to-Text • 8B • Updated • 2.05k
froggeric/Qwen3.6-27B-MLX-4bit
Image-Text-to-Text • 5B • Updated • 1.2k • 1
froggeric/Qwen3.6-27B-MLX-8bit
Image-Text-to-Text • 8B • Updated • 1.08k • 2