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 1 hour ago
froggeric/Qwen-Fixed-Chat-Templates:Will this work on spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit ? new activity about 4 hours ago
froggeric/Qwen3.6-27B-MTP-GGUF:Great model and Jinja upgrade new activity about 4 hours ago
Qwen/Qwen3.5-35B-A3B:fix chat template to avoid empty historical `<think>` blocksOrganizations
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 • 1.02k -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-6bit
Image-Text-to-Text • 6B • Updated • 1.07k • 2 -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
Image-Text-to-Text • 5B • Updated • 3.27k • 3 -
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bit
Image-Text-to-Text • 10B • Updated • 2.85k • 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 • 1.02k -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-6bit
Image-Text-to-Text • 6B • Updated • 1.07k • 2 -
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
Image-Text-to-Text • 5B • Updated • 3.27k • 3 -
froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bit
Image-Text-to-Text • 10B • Updated • 2.85k • 3