• As always, more models are supported. Note that most of the new models are special in some way.

  • Step3-VL: strong vision capability
  • GLM-4.7-Flash: strong coding capability
  • TranslateGemma: translation
  • WeDLM: diffusion with AR
  • QWen3-VL-Embedding/Reranker: multimodal embedding
  • HY-MT: translation
  • GLM-ASR-Nano: ASR
  • Qwen3-VL: strong vision capability

• As always, more models are supported.
• Windows: prebuilt binary with Vulkan (1.4.335.0). Use -ngl all to run whole model on default GPU.
• New server.exe with built-in llama.cpp WebUI

• As always, more models are supported, notably LLaDA2.0.
• Windows: prebuilt binary with Vulkan (1.4.321.1). Use -ngl all to run whole model on default GPU.

• As always, more models are supported, notably Janus-Pro.
• Windows: prebuilt binary with Vulkan (1.4.321.1). Use -ngl all to run whole model on default GPU.

• As always, more models are supported.
• Windows: prebuilt binary with Vulkan (1.4.321.1). Use -ngl all to run whole model on default GPU.

• Fix main_nim.exe: could not download models that are > 2GB due to this.

• As always, more models are supported.
• Windows: prebuilt binary with Vulkan (1.4.321.1). Use -ngl all to run whole model on default GPU.

Update 2025-08-16: chatllm_win_x64.7z updated due to outdated main.exe.

• As always, more models are supported.
• Multimodal: vision & TTS.
• Windows: prebuilt binary with Vulkan (1.4.304.1). Use -ngl all to run whole model on default GPU.

• As always, more models are supported;
• Windows: prebuilt binary with Vulkan (1.4.304.1). Use -ngl all to run whole model on default GPU.

• As always, more models are supported;
• Windows: prebuilt binary with Vulkan (1.4.304.1). Use -ngl all to run whole model on default GPU.