ThoxMini (4 GB) target configuration: THOX configuration (not training) over Qwen2.5-1.5B-Instruct for on-device decision support. 11.35 tok/s (measured 2026-10-31). Not device-qualified. Apache-2.0.
iOS edge model: THOX iOS configuration (not training) over Qwen2.5-1.5B-Instruct for local assistant and routing work. 35.67 tok/s (measured 2026-10-31). Not device-qualified. Apache-2.0.
ThoxClip (6 GB) target configuration: THOX configuration (not training) over Qwen2.5-1.5B-Instruct for on-device decision support. 20.87 tok/s (measured 2026-10-31). Not device-qualified. Apache-2.0.
Qwen2.5-1.5B-Instruct (Q4_K_M), tuned for fast local inference — 5.4x faster than the original with verified quality (perplexity +3%, task scores unchanged).
Gen Z persona chatbot fine-tuned from Qwen2.5-1.5B-Instruct using LoRA. Responds in a casual, slang-heavy conversational style — trained for creative writing and chat use cases rather than technical tasks.
THOX preference- and intent-routing model: a rank-16 LoRA on Qwen2.5-1.5B-Instruct that classifies requests so the stack routes them to the right model or tool. ~0.99 GB Q4_K_M GGUF. THOX-trained adapter. Apache-2.0.
fgptech_2.5-1.5b-code-review Modèle dérivé de Qwen/Qwen2.5-1.5B-Instruct, fine-tuné (SFT + LoRA → fusionné) pour la revue de code (FR) au format strict Markdown.
基于互联网公开数据微调的web3 安全风控大模型；公开数据包括但不限于慢雾科技《区块链黑暗森林自救手册》 等
https://huggingface.co/bartowski/Qwen2.5-Coder-1.5B-Instruct-abliterated-GGUF
Qwen2.5 0.5B and 1.5B instruct fine-tuned with a synthetic dataset
A decensored 1.5B model with strong instruction-following and suppressed refusal behavior. Made by RACER IS OP.
reupload of Qwen2.5-14B-Instruct by Qwen: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-GGUF
Uncensored, abliterated build of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct), Alibaba's capable 14B instruct model
Qwen2.5-7B/14B-Instruct-1M
gte-Qwen2-1.5B-instruct is the model in the gte (General Text Embedding).
This is https://huggingface.co/bartowski/Qwen2.5-14B-Instruct-GGUF