CanItRun Logocanitrun.

GLM-4.7 358B

GLM-4.7 358B needs roughly 203.9GB VRAM at Q4_K_M quantization (805.4GB at FP16). 10 GPUs we track can run it fully in VRAM at 8k context.

Z.ai358B params32B active (MoE)198k contextMITCommercial use ok

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP16716.0 GB3.09 GB805.4 GB
Q8358.0 GB3.09 GB404.4 GB
Q6_K268.5 GB3.09 GB304.2 GB
Q5_K_M223.8 GB3.09 GB254.1 GB
Q4_K_M179.0 GB3.09 GB203.9 GB
Q3_K_M143.2 GB3.09 GB163.8 GB
Q2_K107.4 GB3.09 GB123.8 GB

Benchmarks

GPQA
85.7

GPUs that run GLM-4.7 358B natively (10)

Notes

Flagship 4.x model with interleaved/preserved/turn-level thinking modes. 200K context.

Hugging Face ↗Released 2025-12-22