Zhipu AI/Mixture of Experts

GLM 4.7

Name: GLM 4.7
Author: Zhipu AI

GLM 4.7 — latest in the series with stronger coding and agentic capabilities.

chatcodingreasoningtool_useThinkingTool Use

358B

Parameters (32B active)

193K

Context length

Benchmarks

Quantizations

115K

HF downloads

Architecture

MoE

Released

2026-01-29

Layers

KV Heads

Head Dim

128

Family

glm

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	107.0 GB	low
IQ2_M	2.93	131.6 GB	low
Q2_K	3.16	141.9 GB	low
IQ3_XXS	3.25	145.9 GB	low
IQ3_XS	3.5	157.1 GB	low
Q3_K_S	3.64	163.4 GB	low
IQ3_M	3.76	168.7 GB	low
Q3_K_M	4	179.5 GB	low
Q3_K_L	4.3	192.9 GB	moderate
IQ4_XS	4.46	200.1 GB	moderate
Q4_K_S	4.67	209.5 GB	moderate
Q4_K_M	4.89	219.3 GB	good
Q5_K_S	5.57	249.7 GB	good
Q5_K_M	5.7	255.6 GB	good
Q6_K	6.56	294.0 GB	excellent
Q8_0	8.5	380.9 GB	lossless
FP16	16	716.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN GLM 4.7 NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (14)

τ²-Bench95.9

AIME95.7

AA Math95.0

GPQA Diamond85.7

LiveCodeBench84.9

MMLU-PRO84.3

IFBench67.9

AA Long Context64.0

MATH-50048.0

SciCode45.1

AA Intelligence42.1

AA Coding36.3

Terminal-Bench31.8

HLE24.8

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run glm:358b-q4_K_M

Tag may need adjustment — check ollama.com/library/glm for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware