glm-5

Open repos and models their makers tagged glm-5, most starred first. The same for everyone.

GitHubRepo

Chat2API

Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It supports providers such as DeepSeek, GLM, Kimi, MiniMax, Qwen, and Z.ai, and seamlessly integrates with tools like openlcaw, Cline, and Roo-Code.

  • 1.7k
  • TypeScript
  • 6 mo ago
xiaoY233Take it
AI on my own machineRepo

Xolotl

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s agent, ~41 fast, 512K context. Plus Inkling-2-Mini (own engine: 512K on 24 GB, vision, MTP drafter), GLM-5.3-Flash, Qwen3.8, LFM3-Omni. MoE experts tiered across VRAM, RAM and NVMe (Xolotl Direct). OpenAI + Anthropic API.

  • 560
  • C++
  • MIT
  • 8 h ago
AI on my own machineRepo

mcore-bridge

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3-Next, GLM-5.3, Deepseek-V4, MiniMax-2.7, ...) and 200+ multimodal large models (Qwen3.8, Qwen3-Omni, Gemma4, ...).

  • 107
  • Python
  • Apache-2.0
  • 3 d ago
modelscopeTake it
AI on my own machineRepo

apus-glm5.3-flash

Local inference engine for GLM-5.3-Flash (320B MoE, glm5_next) on consumer hardware — runs the full 306 GiB FP8 model on 32 GB RAM by streaming experts from NVMe. Bitwise-exact C11 engine (NEON/AVX2/Metal), KDA + DSA hybrid attention, mHC, MTP speculative decoding, OpenAI-compatible server. macOS / Linux / Windows.

  • 0
  • C
  • 3 mo ago
bricesommersTake it
Search GitHub and Hugging Face for glm-5

Get , open it once and sign in. Then come back here and press the button again.