全站搜索

AI 模型 85004

• ViT-H-14-CLIPA-336-datacomp1B↗

  UCSC-VLAA

• gemma-4-31B↗

  unsloth

• Olmo-3-7B-Instruct↗

  unsloth

  We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding. Olmo is a series of **O**pen **l**anguage **mo**dels designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets. We are releasing all code, checkpoints, logs (coming soon), and associated training details. The quantized model is more sensitive to data types and CUDA operations. To avoid potential issues, it's recommended to pass the inputs directly to CUDA using:

• Qwen3.8-27B-GGUF↗

  unsloth

  推出 Dynamic V3.0 GGUF，实现 SOTA 精度与量化性能。在 Unsloth Desktop 中运行并微调 Qwen3.8，支持 Thinking 切换。适用于 Mac、Windows 和 Linux。GitHub 仓库开发者角色支持，让 Qwen3.8 能够在 Codex 等智能体工具中发挥作用！工具调用改进：优化嵌套对象解析，提升工具调用成功率。请参阅下方在 Unsloth Desktop 内运行的 4-bit Qwen3.8-27B：最佳 Qwen3.8 GGUF 提供商分析。Unsloth Dynamic v3.0 在同等规模下，相比其他所有提供商，Top-1% 精度提升超过 10%。了解更多。继 Qwen3.5 和 Qwen3.6 系列获得社区广泛采用之后，我们很高兴推出 Qwen3.8——迄今为止 Qwen 开源模型家族中能力最强的一代。

• Khushi-Business-AI-4bit↗

  UX4567

• Tifa-DeepsexV2-7b-MGRPO-GGUF-Q8↗

  ValueFX9507

• Qwen3.8-27B-Fable-Distill-FP8↗

  vwdubb

• grok-4.2-image↗

  xAI

  grok系列的绘图模型

• gemma-4-26B-A4B-it-qat-GGUF↗

  Yiriru

• Qwen-Image-2.1-Uncensored-GGUF↗

  Aero2026