GLM-4-9B-Chat

9B

Zhipu GLM-4

Zhipu GLM-4 open 9B with 128K context, tool calling, and strong bilingual (EN/ZH) performance.

⬇ 17.3K HF downloads♥ 25 likeszai-org/glm-4-9b-chat-hf· stats from 8/8/2026
Consumer GPUMac / Apple Silicon

131K

Max Context

3

Quant Variants

GGUF Q8_0

Best Quality

99.6%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = site benchmarks · Estimated = formula · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.856.2 GB3.0%135 tok/sEstimated
CalcHF
GGUFQ8_08.59.8 GB0.4%105 tok/sEstimated
CalcHF
AWQINT445.5 GB4.2%178 tok/sEstimated
CalcHF

Similar models

Compare with Qwen2.5 14B
14B

Qwen2.5 14B Instruct

Alibaba Qwen2.5

Consumer GPUMac / Apple Silicon
9.2 GBmin VRAM·98.6%accuracy

The sweet spot between performance and resource usage. 16GB VRAM with Q4.

14B

Phi-3 Medium 14B Instruct

Microsoft Phi

Consumer GPUMac / Apple Silicon
8.8 GBmin VRAM·99.2%accuracy

Microsoft's mid-size Phi-3. Excellent quality-per-GB on 16GB cards.

16B

DeepSeek-V2-Lite Chat

DeepSeek

Consumer GPUMac / Apple Silicon
9.6 GBmin VRAM·97.0%accuracy

MoE general model (~2.4B active). Long context and strong multilingual chat.

10B

Falcon 3 10B Instruct

TII UAE

Consumer GPUMac / Apple Silicon
6.2 GBmin VRAM·96.9%accuracy

Technology Innovation Institute's latest Falcon. Good multilingual and code mix.