Z.ai
GLM-5.2 (753.2999877929688B parameters) requires approximately 481.6 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 40B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 554 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run GLM-5.2 on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "zai-org/GLM-5.2" \
--hf-file "GLM-5.2-Q4_K_M.gguf" \
-c 4096 -ngl 99Quick specs
About this model
Related models
Inference speed
Estimated decode speed (tokens/sec) for GLM-5.2 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~2 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 2.0 | Too big |
| RTX 4090 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 2.0 | Too big |
| RTX 3090 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
| RTX 4070 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 2.0 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.0 | Too big |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 2.0 | Too big |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 2.0 | Too big |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 2.0 | Too big |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 2.0 | Too big |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 2.0 | Too big |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 2.0 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 2.0 | Too big |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 2.0 | Too big |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 2.0 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 293.8 GB | Low | — |
Q3_K_S | 3 | 369.1 GB | Low | — |
NVFP4 | 4 | 421.8 GB | Medium | — |
Q4_K_M | 4 | 459.5 GB | Medium | — |
Q5_K_M | 5 | 542.4 GB | High | — |
Q6_K | 6 | 617.7 GB | High | — |
Q8_0 | 8 | 806.0 GB | Very High | — |
F16 | 16 | 1544.3 GB | Maximum | — |
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
GLM-5.2 (753.2999877929688B parameters) requires approximately 481.6 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
The recommended quantization for GLM-5.2 is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
Yes, GLM-5.2 is well-suited for chat as well as coding, reasoning, agentic. It was designed with these use cases in mind.
See also