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.
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
Reviewed quality benchmarks
First-party rows were run by RunLocalAI; reviewed community rows are labeled in the data. Every row links to the raw test-run log.
| Benchmark | Quant | Runtime / Hardware | Score | Raw log |
|---|---|---|---|---|
HumanEval+ tested 2026-07-21 | Q4_K_M | ollama-0.32.1-vast5090 rtx-5090 | 85.4/100 | Gist → |
Q4_K_M note:First-party HumanEval+ on a rented Vast.ai RTX 5090 32GB instance via Ollama 0.32.1. Generation via evalplus_openai_generate.py, scoring via evalplus.evaluate (native Linux, no Windows shim needed). No DB credentials were placed on the rented host — results were pulled back and ingested from the operator's machine.
Want to verify? Every row links to its Gist with full stdout and stderr of the run. The runner script is in the public repo (scripts/run-humaneval-plus.ts) — reproducible end-to-end. Browse all coding scores at /benchmarks/coding.
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 19.0 GB | 23 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.
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?
Can I use GLM-4.7-Flash commercially?
What's the context length of GLM-4.7-Flash?
How do I install GLM-4.7-Flash with Ollama?
Source: Vendor official documentation
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify GLM-4.7-Flash runs on your specific hardware before committing money.