FOXAI SEARCH
全站搜索
AI 模型 85012
- Mamba-Codestral-7B-v0.1-Q4_K_M-GGUF↗
viniciusianni
- Qwen3-VL-8B-Instruct-W4A16-AutoRound-AWQ↗
Vishva007
This model is the **AWQ (Activation-aware Weight Quantization)** export of Qwen/Qwen3-VL-8B-Instruct. It combines the **speed of AWQ** with the **accuracy of AutoRound**. The weights were fine-tuned for 800 steps to ensure the 4-bit degradation is negligible. The vision tower remains in full precision (FP16) to maintain top-tier performance on OCR and visual tasks. One-click launch environments pre-configured with PyTorch, CUDA, and dependencies for fine-tuning or quantization.
- NVIDIA-Nemotron-Nano-9B-v2-gguf↗
weathermanj
- EVE-27b-XENO-HAT-DeepSeek-V4-Flash↗
win10
This is a cross-architecture model merge, with the architecture aligned to the QWEN 3.5 architecture.
- InstructPalmyra-20b↗
Writer
- bert-base-uncased_sts_mrpc_houlsby↗
AdapterHub
- indic-parler-tts↗
ai4bharat
- IndicBART-XLSum↗
ai4bharat
- core-reranker-8b↗
Alibaba-NLP
- Vex-Amber-Fable-2.0↗
Arioron
