GLM 4.7 vs GLM 5

Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.

GLM 4.7

zai-org · 358.3B

Chat
GLM 5

zai-org · 753.9B

Chat

Specifications

GLM 4.7GLM 5
Parameters358.3B753.9B
Context203K203K
ArchitectureGlm4MoeForCausalLMGlmMoeDsaForCausalLM
LicenseMITMIT
Downloads66.2K199.0K
ReleasedJan 2026Mar 2026

VRAM by Quantization: GLM 4.7 vs GLM 5

QuantizationBitsGLM 4.7 VRAMGLM 5 VRAM
Q2_K3.40152.9 GB324.6 GB
Q3_K_M3.90175.3 GB371.7 GB
Q3_K_S3.50157.4 GB334.0 GB
Q4_04.00179.8 GB381.2 GB
Q4_K_M4.80215.6 GB456.5 GB
Q5_K_M5.70255.9 GB541.4 GB
Q6_K6.60296.3 GB626.2 GB
Q8_08.00359.0 GB758.1 GB

Verdict

GLM 4.7 needs less VRAM at Q4_K_M (215.6 GB vs 456.5 GB), so it fits on smaller GPUs. GLM 5 is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, GLM 4.7 or GLM 5?

At Q4_K_M, GLM 4.7 needs 215.6 GB and GLM 5 needs 456.5 GB, so GLM 4.7 is the lighter option to run locally.

Which has a longer context window, GLM 4.7 or GLM 5?

GLM 4.7 supports 202,752 tokens and GLM 5 supports 202,752 tokens.

What is the difference between GLM 4.7 and GLM 5?

GLM 4.7 is a 358.3B model from zai-org (GLM family), while GLM 5 is a 753.9B model from zai-org (GLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.