GLM-4.7-Flash

GLM-4.7-Flash is designed as a pragmatic, high-performance alternative to larger, more complex systems. While its flagship counterpart utilizes a massive Mixture-of-Experts architecture, this model employs a streamlined, dense 30-billion parameter structure. This design choice ensures that every parameter is utilized for every token processed, resulting in highly predictable inference behavior and consistent latency. By focusing on a dense architecture, the model offers a reliable and efficient solution for teams that require robust code generation and reasoning capabilities without the hardware management challenges often associated with larger, sparse models.

Built to serve as a workhorse for developers, the model excels in real-world coding tasks and complex tool-calling scenarios. Its architecture simplifies quantization and deployment on local hardware, making it a versatile choice for engineers looking to integrate agentic workflows into smaller-scale environments. With a substantial context window, it is well-suited for processing full repository contexts, extensive documentation, and detailed stack traces. As a dense model, it provides a stable foundation for those seeking a balance between high-level performance and the practical constraints of budget and infrastructure.

Z.AIglm-4.7-flashglm-flash

Open provider page Provider docs

Quick Info

Provider: Z.AI
Model key: glm-4.7-flash
Release date: Jan 19, 2026
Last updated: Jan 19, 2026
Knowledge cutoff: 2025-04
Input modalities
Output modalities
Capabilities

Cost

A provider subscription or plan supersedes token-based pricing for this model.

Limits

Output tokens: 131,072 tokens
Context window: 200,000 tokens

Latest news about GLM-4.7-Flash

Z.AI

CoverageBenchmark

GLM-4.7 Flash packs 31B parameters and an MIT license with free API access, helping you test ideas and ship tools on a tiny budget.

Z.AI

CoverageBenchmark

Z.AI's GLM-4.7 Flash is a 31-billion-parameter open-source model released for coding, reasoning, and agentic workflows, offering free API access and local deployment. It records 59% on Software Engineering Bench, 79.5% on TA2 agentic tasks, and 75.2% on GPQA, while pricing lists $0.07 input, $0.01 cached input, and $0.

Z.AI

Coverage

The 30B model achieves 59.2% on SWE-bench Verified while running at 80+ tokens per second on MacBooks.

Z.AI

CoverageRelease Notes

Zhipu AI Releases GLM-4.7-Flash: A 30B-A3B MoE (Mixture of Experts) Model for Efficient Local Coding and Agents.

Z.AI

Coverage

Excerpt): Zhipu AI has open-sourced GLM-4.7-Flash, a 30B-parameter MoE model that activates only 3B during inference. Notably, it debuts the MLA architecture for efficiency and runs at 43 tokens/sec on an Apple M5 laptop.

Z.AI

Coverage

The Hacker News thread on GLM-4.7-Flash (378 points, 135 comments, submitted by scrlk) captures community testing of the model in OpenCode running local 30B-A3B quantizations via llama.cpp on a 32 GB GPU with 128k context. One commenter reports that Qwen3-Coder had previously given the best results in their workflow of Early user issues documented in the thread include broken tool calling in OpenCode, rapid self-repetition (mitigated by raising llama.cpp's --dry-multiplier to 1.1 or higher), and spelling errors such as class or file-name characters being replaced with "1" or "AGENTS.md" being misread as "AGANTS.md". A later reply ann

Z.AI

CoverageBenchmark

AIbase reports that Zhipu AI officially open-sourced GLM-4.7-Flash in the early hours of January 20, 2026, framing it as a "Hybrid Thinking" model and the strongest competitor in the 30B specification class. The article confirms the 30B-A3B MoE design, where approximately 3 billion of 30 billion parameters activate per The excerpt lists the same vendor-published benchmark scores: 59.2 on SWE-bench Verified for code repair, 91.6 on AIME25 and 75.2 on GPQA for math and expert-level reasoning, 79.5 on τ²-Bench and 42.8 on BrowseComp for tool collaboration and agent scenarios. These figures are reported as surpassing Alibaba's Qwen3-30B-