THOX on-device assistant for small edge devices: 873M Qwen3.5-0.8B fine-tune on THOX chat and tool-use corpora; Q4_K_M GGUF 529 MB. EXPERIMENTAL: no published benchmark or training log yet. Apache-2.0.
ThoxEdge flagship for ThoxMini, THOX fine-tuned into Qwen3.5-0.8B (QLoRA merged), thinking-off. GATE49 46/49 (development set). Q4_K_M GGUF 0.53 GB. Apache-2.0.
A compact Qwen3.5-0.8B reasoning model improved through Weight-Space Programming. Features targeted weight modifications designed to reduce repetitive reasoning loops and improve mathematical reasoning.
Text-only Qwen3.5 0.8B GGUF files. Default: q5_k_m. TurinTech models, built with Artemis. Measured Q5_K_M: Mean KLD 0.0098, Same top p 94.2% vs BF16 on WikiText-2 test; protocol rtx5090-2026-10-20.
Qwen3.5 0.8B in Q8_0 quantization. Small, fast model with 262K context, vision, tool use, and thinking capabilities. Optimized for local/edge deployment on constrained hardware.
A lightweight Havenlon-focused Qwen3.5 0.8B model for execution-boundary concepts, local policy reasoning, and constrained edge deployment.
A lightweight but surprisingly capable reasoning model — distilled from Claude 4.6 Opus, quantized to Q4_K_M for local use.
WSAI-Math 是 WSAI 开发的数学推理大语言模型，基于 Qwen3.5-0.8B 后训练而成，采用 Apache-2.0 许可。
基于 Qwen3.5-0.8B 微调的心理支持对话模型，擅长情感陪伴与心理疏导。体积小、支持 CPU 端侧部署。
A Medical Optimized Version Based On Qwen 3.5 0.8B