Can GLM 4.5V run on the Mac M2 Ultra 192GB?
Yes. At 8K context the best fit is Q8_0, using about 108 GB of the 144 GB usable on the Mac M2 Ultra 192GB. Estimated speed ceiling: ~53 tokens/sec.
+ 0.9 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q8_0 at 8K context then needs about 109 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 39.0 GB Fits | 39.7 GB Fits | 44.1 GB Fits | 149 |
| 3-bit (Q3_K_M) | 50.4 GB Fits | 51.2 GB Fits | 55.5 GB Fits | 115 |
| 4-bit (Q4_K_M) • | 60.7 GB Fits | 61.4 GB Fits | 65.7 GB Fits | 95 |
| 5-bit (Q5_K_M) | 72.9 GB Fits | 73.6 GB Fits | 77.9 GB Fits | 79 |
| 6-bit (Q6_K) | 83.7 GB Fits | 84.4 GB Fits | 88.7 GB Fits | 68 |
| 8-bit (Q8_0) • | 107 GB Fits | 108 GB Fits | 112 GB Fits | 53 |
| 16-bit (F16/BF16) | 202 GB No | 203 GB No | 207 GB No | — |
• real GGUF file size from ggml-org/GLM-4.5V-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs GLM 4.5V: DGX Spark (128 GB, launch MSRP $3,999) at Q6_K, fully in VRAM at 8K context.
- Largest popular model that fits the Mac M2 Ultra 192GB: Qwen3.8 Flash Next (180B, MoE) at Q5_K_M, about 126 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
GLM 4.5V on every GPU and Mac · Every model that runs on the Mac M2 Ultra 192GB · Apple Silicon guide · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (zai-org/GLM-4.5V), Apple specs. Model data last checked 2026-11-18; refreshed hourly.