Overview
GLM-4.7-Flash is a 31.2B-parameter open-weight model from zai-org (Z.ai), the team behind the GLM-4.5 and GLM-4.7 series.
- License: Mit
- Context length: 128K tokens
- Languages: Multilingual
- Minimum hardware: ~64 GB VRAM
- Strengths: fast MoE chat, coding and tool use
Highlights
- Fast MoE chat — a 30B-A3B mixture-of-experts model tuned for speed.
- Tool use & thinking mode — calls functions and reasons step by step before answering.
- Coding assistant — writes, refactors, and debugs across files.
- 128K context — reasons over long documents and large repositories.
What it is good at
GLM-4.7-Flash ships with tool use, reasoning, and a thinking mode, which lines up with a few practical jobs:
- Local coding assistant — its
codecapability handles writing functions, refactoring, and debugging across files, with reported speeds around 60-100 tokens per second on consumer GPUs. - Agentic workflows — the
toolscapability lets it call functions and chain steps, so you can wire it into local agents that read files or hit APIs without sending data to a cloud provider. - Step-by-step reasoning — the thinking mode works through math, logic, and multi-part questions before answering, and the 128K context lets it reason over long documents or large code repositories in one pass.
Running it locally
The model is 31.2B parameters total with a 128K context window. A 4-bit quantization runs on roughly 16GB of VRAM (an RTX 3090 or 4090, or an M-series Mac), while full BF16 precision wants around 64GB. Pull the weights with the Hugging Face CLI:
huggingface-cli download zai-org/GLM-4.7-Flash
From there you can serve it with Transformers or vLLM, run a quantized GGUF in llama.cpp, or load it one-click in Atomic Chat and start chatting on-device.
License
GLM-4.7-Flash is released under the MIT license. That permits commercial use, modification, and redistribution, as long as you keep the copyright and license notice — among the most permissive terms an open-weight model can carry.