Zhipu on Apple M3
Can I run GLM-4 9B on an Mac Studio M3 Ultra 256GB?
Yes. GLM-4 9B at Q4_K_M uses 6.2 GB of the 192.0 GB available on a Mac Studio M3 Ultra 256GB, and runs at about 83.4 tokens per second. You can push the context to 128K.
Runs comfortably
6.2 GB of 192.0 GB · 3%0192 GB
Weights
5.4 GB
KV cache
0.3 GB
Runtime overhead
0.5 GB
GLM-4 9B at Q4_K_M leaves 185.8 GB spare on a Mac Studio M3 Ultra 256GB. There is room to raise the context length or move up a quantisation level.
Generation83.4tok/s
Prompt processing1273tok/s
Max context128Ktokens
KV per 1K tokens0GB
Every quantisation of GLM-4 9B on a Mac Studio M3 Ultra 256GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 17.5 GB | 18.3 GB | Runs comfortably | 128K | 26.6 |
| INT8 / W8A8 | 8.50 | 9.0 GB | 9.9 GB | Runs comfortably | 128K | 50.9 |
| Q8_0 (GGUF) | 8.50 | 9.0 GB | 9.9 GB | Runs comfortably | 128K | 50.9 |
| FP8 (E4M3) | 8.00 | 8.8 GB | 9.6 GB | Runs comfortably | 128K | 52.4 |
| Q6_K | 6.56 | 7.2 GB | 8.0 GB | Runs comfortably | 128K | 63.5 |
| AWQ 4-bit | 4.25 | 6.3 GB | 7.2 GB | Runs comfortably | 128K | 71.5 |
| GPTQ 4-bit | 4.25 | 6.3 GB | 7.2 GB | Runs comfortably | 128K | 71.5 |
| MXFP4 | 4.25 | 6.3 GB | 7.2 GB | Runs comfortably | 128K | 71.5 |
| Q5_K_M | 5.67 | 6.2 GB | 7.0 GB | Runs comfortably | 128K | 73.1 |
| Q5_K_S | 5.52 | 6.0 GB | 6.9 GB | Runs comfortably | 128K | 75.0 |
| Q4_K_M | 4.85 | 5.4 GB | 6.2 GB | Runs comfortably | 128K | 83.4 |
| Q4_K_S | 4.58 | 5.1 GB | 6.0 GB | Runs comfortably | 128K | 87.4 |
| Q4_0 | 4.55 | 5.1 GB | 5.9 GB | Runs comfortably | 128K | 87.9 |
| IQ4_XS | 4.25 | 4.8 GB | 5.7 GB | Runs comfortably | 128K | 92.8 |
| Q3_K_M | 3.91 | 4.5 GB | 5.3 GB | Runs comfortably | 128K | 99.0 |
| IQ3_M | 3.70 | 4.3 GB | 5.1 GB | Runs comfortably | 128K | 103 |
| IQ3_XXS | 3.06 | 3.7 GB | 4.5 GB | Runs comfortably | 128K | 119 |
| Q2_K | 2.63 | 3.3 GB | 4.1 GB | Runs comfortably | 128K | 133 |
| IQ2_XXS | 2.06 | 2.8 GB | 3.6 GB | Runs comfortably | 128K | 157 |
| IQ1_M | 1.75 | 2.5 GB | 3.3 GB | Runs comfortably | 128K | 174 |