GLM-4.7-Flash — The 30B Lightweight GLM Model

GLM-4.7-Flash is the 30-billion-parameter member of the GLM model family, built for the case where the flagship simply will not fit. Thirty billion parameters is the size class that runs on a single high-memory accelerator, or quantised on consumer hardware, which makes it the natural choice for local development, on-premise inference and anything where per-request latency matters more than the last few benchmark points.

The model authors position it as efficient and high-performance, and report that it outranks open-source models of a similar scale. That claim is the relevant one for this tier: nobody deploying a 30B model expects it to beat a frontier system, but they very much care whether it beats the other 30B options they could have run instead.

30B
parameters
the size class that fits a single accelerator
MIT
open-source license
MIT, with no regional restrictions
4.7
series generation
the lightweight tier of the GLM-4.7 line

Free AI Playground — Try a Live Open-Source LLM

No sign-up, no account, no credits. Type a prompt and get a streamed answer.

Response will stream here...

This playground runs a free open-source LLM via OpenRouter. It is not GLM-5.2 and does not use GLM weights — it's here so you can test a live model while you read the published GLM benchmark data below.

Why a 30B GLM Model Is Worth Having

Parameter count decides where a model can physically run, and that constraint drives more architecture decisions than raw capability does. A 30B model can be served on hardware a small team already owns, keeps prompts inside your own network, and answers fast enough to sit in an interactive loop rather than a batch queue. It is also the size at which fine-tuning stops being a research project — you can adapt a 30B GLM model to a narrow domain and still evaluate the result in an afternoon. The trade is real: fewer parameters means less headroom on hard, long-horizon reasoning, which is exactly the workload the 1M-context flagship was built for. The right way to use the family is to route work by difficulty, keeping cheap, high-volume tasks on Flash and reserving the flagship for problems that genuinely need it.

Parameters
30B
License
MIT open source
Positioning
Lightweight, high throughput
Family
GLM-4.7 series
Weights host
HuggingFace · ModelScope

GLM-4.7-Flash in the Published Benchmark Data

The published comparison table covers GLM-5.2 and GLM-5.1. The column below is GLM-5.1's, shown only as a reference point for the family. No benchmark column has been published for GLM-4.7-Flash, and none is estimated here.

There is no published GLM-4.7-Flash row, and inferring one from a much larger model would be misleading in either direction. What the reference column is good for is calibration: it shows the spread the published GLM models occupy, so you know what a full-size model of the previous generation achieved before you decide whether a 30B model is likely to be adequate for your task.

See all 17 GLM benchmarks in detail →

How the Family Compares on Long-Horizon Coding

Comparison on DeepSWE, as published by the model authors.

DeepSWE is where model scale shows up most brutally. GPT-5.5 leads at 70.0 and Claude Opus 4.8 posts 58.0, GLM-5.2 reaches 46.2, and the previous open generation clusters far below — GLM-5.1 and Qwen3.7-Max at 18.0, DeepSeek-V4-Pro at 8.0. If your workload looks like DeepSWE, a lightweight model is the wrong tool no matter how efficient it is; if it looks like classification, extraction or routine code edits, Flash is likely all you need.

Read the full GLM vs Qwen comparison →

Where GLM-4.7-Flash Sits in the GLM Model Lineup

GLM-4.7-Flash is the lightweight tier of the GLM-4.7 generation, sitting alongside the full-size GLM-4.7 and above the older GLM-4.5-Air in the family's efficiency line. Everything in that line carries the same MIT license and the same weight hosts, so moving between tiers is a hardware decision, not a legal one.

More GLM Models

View all

GLM-4.7-Flash FAQ

What is the GLM-4.7-Flash model?
GLM-4.7-Flash is the 30-billion-parameter lightweight member of the GLM model family. It is MIT licensed with open weights, built for efficient high-throughput inference, and reported by the model authors to outrank open-source models of a similar scale.
What hardware do I need to run GLM-4.7-Flash?
Thirty billion parameters is the size class that fits on a single high-memory accelerator at reduced precision, or on consumer hardware once quantised. Exact requirements depend on your quantisation, context length and serving framework, so measure with your own configuration rather than trusting a rule of thumb.
Does GLM-4.7-Flash have published benchmark scores?
Not in the comparison table the model authors published, which covers GLM-5.2 and GLM-5.1. This site does not estimate a column for it. The published claim for this model is a relative one: it is reported to outrank open models of a similar scale.
Is GLM-4.7-Flash open source?
Yes. It is an MIT-licensed open-weight GLM model published on HuggingFace and ModelScope with no regional restrictions, and it runs on transformers, vLLM, SGLang, xLLM and ktransformers like the rest of the family.
GLM-4.7-Flash or GLM-4.5-Air?
Flash is the newer lightweight tier and carries the GLM-4.7 generation's programming and reasoning improvements; Air is the earlier efficiency milestone. Neither has a published benchmark column, so if both fit your hardware the sensible approach is to evaluate them on your own task rather than on positioning.

Try a Live AI Model Free — No Account Needed

Read the GLM model benchmarks, then put a real model to work. The playground above is free and needs nothing from you; if you want a fuller AI toolkit, our partner's free tier starts here.