GLM-4.7 is a 358-billion-parameter MoE model (MIT) with a 128k context. A large GLM-4 MoE for production reasoning and tool use. It is a frontier-scale model, which makes the local question blunt: for almost everyone, you do not run this on your own hardware. Here is exactly why, and the cheaper path.
The short answer
Only the largest machines we track can hold GLM-4.7, and only at a heavy quant. Here are the ones that fit: For a model this size, renting a cloud GPU or using a hosted API is almost always the saner option.
| Machine | Memory | Quant | Weights | ~tok/s |
|---|---|---|---|---|
| Mac Studio, 512GB unified (Ultra) | 512 GB (unified) | Q8_0 | ~380.4 GB | ~2 tok/s |
The memory math
Weights scale with parameters. At Q4_K_M (about 4.8 bits) GLM-4.7 is roughly 215 GB of weights; squeezed to a low-quality Q2 it is still about 150 GB, before you add the KV cache and overhead. That puts it in a 512 GB Mac Studio (at a heavy quant) or a multi-GPU server territory, not consumer hardware. The VRAM guide and the quantization guide walk through the trade-offs.
Or just rent it (the realistic option)
At this scale, renting a GPU by the hour or calling a hosted API almost always beats buying. Our cost calculator does the buy-versus-rent-versus-API math for your actual usage, so you can see the break-even instead of guessing.
Check the details
- Can I Run It? confirms the fit against any specific machine, including your own.
- All hardware, one sortable chart shows the biggest boxes we track.
- Cost calculator for the rent-versus-buy decision.
Sources and method
- Memory requirements computed from the model's parameter count and standard quant bit-rates with the same engine as our calculator.
- A fit-and-feasibility reference, not first-hand testing by Vetted Consumer. Verify the model's exact parameter and active-parameter counts on its model card before relying on the numbers.