GLM 4.7 Flash Heretic 1.2.0 vs GLM 4.5 Air

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

GLM 4.7 Flash Heretic 1.2.0

darkc0de · 29.9B

Chat
GLM 4.5 Air

zai-org · 110.5B

Chat

Specifications

GLM 4.7 Flash Heretic 1.2.0GLM 4.5 Air
Parameters29.9B110.5B
Context203K131K
ArchitectureGlm4MoeLiteForCausalLMGlm4MoeForCausalLM
LicenseMITMIT
Downloads333359.8K
ReleasedFeb 2026Aug 2025

VRAM by Quantization: GLM 4.7 Flash Heretic 1.2.0 vs GLM 4.5 Air

QuantizationBitsGLM 4.7 Flash Heretic 1.2.0 VRAMGLM 4.5 Air VRAM
Q2_K3.4013.8 GB47.4 GB
Q3_K_M3.9015.7 GB54.3 GB
Q3_K_S3.5014.2 GB48.8 GB
Q4_04.0016.1 GB55.7 GB
Q4_K_M4.8019.1 GB66.7 GB
Q5_K_M5.7022.4 GB79.1 GB
Q6_K6.6025.8 GB91.6 GB
Q8_08.0031.0 GB110.9 GB

Verdict

GLM 4.7 Flash Heretic 1.2.0 needs less VRAM at Q4_K_M (19.1 GB vs 66.7 GB), so it fits on smaller GPUs. GLM 4.7 Flash Heretic 1.2.0 supports a longer context window (203K tokens). GLM 4.5 Air is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, GLM 4.7 Flash Heretic 1.2.0 or GLM 4.5 Air?

At Q4_K_M, GLM 4.7 Flash Heretic 1.2.0 needs 19.1 GB and GLM 4.5 Air needs 66.7 GB, so GLM 4.7 Flash Heretic 1.2.0 is the lighter option to run locally.

Which has a longer context window, GLM 4.7 Flash Heretic 1.2.0 or GLM 4.5 Air?

GLM 4.7 Flash Heretic 1.2.0 supports 202,752 tokens and GLM 4.5 Air supports 131,072 tokens.

What is the difference between GLM 4.7 Flash Heretic 1.2.0 and GLM 4.5 Air?

GLM 4.7 Flash Heretic 1.2.0 is a 29.9B model from darkc0de (GLM family), while GLM 4.5 Air is a 110.5B model from zai-org (GLM family). Compare their VRAM requirements above to see which fits your GPU or Mac.