Work coding build: Qwen3-14B weights configured (not trained) by THOX with the coding profile, workgroup prompt pack, and Knowledge Pack v0.1. 26.28 tok/s, 10.49 GB, grounding 8/8. Apache-2.0.
High laptop tier: Qwen3-14B weights configured (not trained) by THOX with the Open system profile and Knowledge Pack v0.1. Grounding 8/8, routing passed (measured 2026-11-01). Apache-2.0.
Qwen3-14B v2 with network transparency: announces host, country and direction of every connection. IT/EN. Apache-2.0. Limits declared: IFEval −0.4 pt, leak 1.11% vs 1% gate.
Mesh routing build: Qwen3-14B weights configured (not trained) by THOX with the MeshStack expansion profile and Knowledge Pack v0.1. 25.25 tok/s, 10.49 GB, grounding 8/8. Apache-2.0.
DigitalHuman reasoning build: Qwen3-14B weights configured (not trained) by THOX with a persona-following profile, reasoning prompt pack, and Knowledge Pack v0.1. 27.67 tok/s, grounding 8/8. Apache-2.0.
Infinitech Short description A powerful local AI assistant built on Qwen3 14B for reasoning, coding, problem-solving, and clear technical communication. Full description Infinitech is a thoughtful and capable local AI assistant powered by Qwen3 14B. It is
Abliterated Qwen3-14B with 80% reduced refusals while preserving coherence (KL 0.98)
包含2个量化版本GGUF：Qwen3-14B-Q5_K_M，Qwen3-14B-Q8_0
Base model
Qwen3-14B finetuned on helpsteer3
https://huggingface.co/tvall43/Qwen3.6-14B-A3B-VibeForged-v2-GGUF
Compassionate mental health support AI fine-tuned from Qwen 3 (14B) with 128K context.
Thinker is a Qwen 3 14B Q8-based reasoning and writing model designed for structured analysis, planning, documentation, and deep technical explanations
notConfucius.v2 is a fine-tuning experiment. qwen3-14b base with a better designed dataset to reflect a particular cognitive persona - wiser, more coherent, less maddening, and still occasionally enlightening. it’s less a model and more a vibe.
Qwen 3.8 27B (IQ4_XS) - Optimized for 16GB VRAM
Based on Qwen3.5-122B-A10B and converted from the MLX Community 4-bit release (https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-4bit)
Mixed-precision quant of Qwen3.6-35B-A3B: 8-bit attention, 4-bit experts.
Custom model for coding with agents to use locally with 24gb GPUs - BEST FOR OPENCODE!