How much memory does GLM-4.7 Flash need?
About 21 GB at Q4_K_M with an 8K context. It runs on a Mac with 32 GB of unified memory or more.
Try other settings in the calculatorMemory by quantization and context
Total memory: weights, KV cache in F16 and about 1 GB of buffers. Under each total, the smallest Mac that can run it with the default GPU memory limit.
| Quantization | 8K context | 32K context | 128K context |
|---|---|---|---|
| Q3_K_M | 17 GB24 GB Mac | 18 GB32 GB Mac | 23 GB32 GB Mac |
| Q4_K_M | 21 GB32 GB Mac | 22 GB32 GB Mac | 27 GB48 GB Mac |
| Q5_K_M | 24 GB32 GB Mac | 25 GB48 GB Mac | 30 GB48 GB Mac |
| Q6_K | 27 GB48 GB Mac | 28 GB48 GB Mac | 34 GB48 GB Mac |
| Q8_0 | 35 GB48 GB Mac | 36 GB48 GB Mac | 41 GB64 GB Mac |
| F16 | 64 GB96 GB Mac | 65 GB96 GB Mac | 71 GB96 GB Mac |
About the model
- Parameters
- 31.22B
- Type
- Mixture of experts, 64 experts
- Attention
- compressed latent attention (MLA)
- KV cache, F16
- 0.4 GB at 8K, 7.1 GB at 128K
- On Hugging Face
- zai-org/GLM-4.7-Flash
Each layer caches one compressed latent per token instead of full keys and values, which keeps the KV cache small for a model this size. As a mixture-of-experts model it loads every expert into memory, so memory follows the total parameter count, while speed follows the smaller number of active parameters.
Questions
How much memory does GLM-4.7 Flash need?
About 21 GB at Q4_K_M with an 8K context: 19 GB of weights, 0.4 GB of KV cache and about 1 GB of buffers. At 32K context it needs about 22 GB.
Can GLM-4.7 Flash run on a Mac?
Yes. At Q4_K_M with an 8K context it fits on a Mac with 32 GB of unified memory or more, using the default GPU memory limit of about three quarters.
How big is the GLM-4.7 Flash KV cache?
About 0.4 GB at 8K tokens and 7.1 GB at 128K tokens with an F16 cache. Its attention design: compressed latent attention (MLA).
Other models
- Gemma 4 12B
- gpt-oss 20B
- Gemma 4 26B-A4B
- Qwen3.8 27B
- Gemma 4 31B
- Qwen3.6 35B-A3B
- gpt-oss 120B
- Mistral Medium 3.5
- Qwen3.8 Flash Next
- DeepSeek V4 Flash
- GLM-5.3
- DeepSeek V4 Pro
- Kimi K3
Data read from Hugging Face on 2026-11-09. These are estimates; benchmarks on this site report measured memory. How the estimate works. Compare all models in the model fit chart.
Get the next one
New benchmarks and agent runs by email, with the raw data. Or follow on RSS or X.