Models / Run locally

Run GLM-5.2 locally

Z.ai · ≈355B-class MoE (≈32B active) · open weights

≈210GB at 4-bit: multi-GPU server or high-memory Mac Studio. Z.ai's generous hosted free tier is the practical way to try it before committing hardware.

By quantization

Hardware requirements

Quantization≈ File size≈ Memory neededRuns on
Q4_K_M (4-bit)206 GB237 GBMulti-GPU servers (4–8× 80GB) or 512GB Mac Studio clusters
Q8_0 (8-bit)380 GB437 GBMulti-GPU servers (4–8× 80GB) or 512GB Mac Studio clusters
FP16 (full)746 GB858 GBMulti-node GPU clusters — datacenter serving only

Sizes are computed from the ≈355B parameter count with standard GGUF math and ~15% runtime overhead — verify against the model card before buying hardware. As a mixture-of-experts model only ≈32B parameters are active per token, which helps speed — but the full weights still have to fit in memory.

Local setup

How to run it

Grab a community GGUF conversion from Hugging Face and serve it with llama.cpp, LM Studio, or (for multi-GPU rigs) vLLM with the original weights. Pick the quantization from the table above that fits your memory.

For serious throughput on server hardware, vLLM with tensor parallelism is the standard serving stack; llama.cpp and MLX (Apple silicon) win below that line.

The API route

Or skip the GPU entirely

The same model is one API call away at $0.5 / M input · $1.8 / M output — no download, no VRAM math, metered to the exact call. Free starter credits cover your first runs, and because the weights are open, nothing locks you in: start metered, move to your own hardware if sustained volume ever justifies it.

FAQ

Frequently asked questions

Can my GPU run GLM-5.2?

GLM-5.2 is ≈355B-class MoE (≈32B active). At 4-bit quantization you need roughly 237GB of memory (multi-gpu servers (4–8× 80gb) or 512gb mac studio clusters). ≈210GB at 4-bit: multi-GPU server or high-memory Mac Studio. Z.ai's generous hosted free tier is the practical way to try it before committing hardware.

Is there a GLM-5.2 GGUF?

Open-weight releases in this family get community GGUF conversions on Hugging Face shortly after release — search the model name plus "GGUF" and pick the quantization your memory allows from the table above.

Is running GLM-5.2 locally cheaper than the API?

Only at sustained volume. The API price is $0.5 / M input · $1.8 / M output with no hardware, electricity, or ops cost — a machine that can serve this model costs more per month idle than most teams' entire inference bill. Prototype metered, self-host when utilization justifies it.

Can I use the outputs commercially?

Open weights; commercial use permitted per the Z.ai model license.

Explore

Run other models locally

One key. Every model. Exact prices.

Prototype on GLM-5.2 with free starter credits while the weights download. Free starter credits included — no subscription required.