glm
31B parameters
Commercial OK
Reviewed July 2026

GLM-4.7-Flash

GLM-4.7-Flash, released January 19, 2026, is Zhipu's lightweight sibling of the 355B-class GLM-4.7 flagship: a 31B-A3B MoE under MIT, built for local coding and agent workloads. Ollama describes it as the strongest model in the 30B class, with 1.4M pulls in its first month.

License: MIT·Released Jan 19, 2026·Context: 202,752 tokens

Overview

GLM-4.7-Flash, released January 19, 2026, is Zhipu's lightweight sibling of the 355B-class GLM-4.7 flagship: a 31B-A3B MoE under MIT, built for local coding and agent workloads. Ollama describes it as the strongest model in the 30B class, with 1.4M pulls in its first month.

Strengths

  • MIT license — the least restrictive terms of any model in this campaign
  • MoE (3B active of 31B total) gives fast decode for its size class
  • 1.4M pulls in the first month signals strong early adoption

Weaknesses

  • Distilled/lite sibling of GLM-4.7 — trades some capability for speed versus the 355B flagship
  • One month of public track record at time of this benchmark

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M19.0 GB23 GB

Get the model

Ollama

One-line install

ollama run glm-4.7-flashRead our Ollama review →

Hardware that runs this

Cards with enough VRAM for at least one quantization of GLM-4.7-Flash.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Frequently asked

What's the minimum VRAM to run GLM-4.7-Flash?

23GB of VRAM is enough to run GLM-4.7-Flash at the Q4_K_M quantization (file size 19.0 GB). Higher-quality quantizations need more.

Can I use GLM-4.7-Flash commercially?

Yes — GLM-4.7-Flash ships under the MIT, which permits commercial use. Always read the license text before deployment.

What's the context length of GLM-4.7-Flash?

GLM-4.7-Flash supports a context window of 202,752 tokens (about 203K).

How do I install GLM-4.7-Flash with Ollama?

Run `ollama pull glm-4.7-flash` to download, then `ollama run glm-4.7-flash` to start a chat session. The default quantization is Q4_K_M.

Source: Vendor official documentation

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Before you buy

Verify GLM-4.7-Flash runs on your specific hardware before committing money.