Can I run GLM-5.2 on a M5 Max 64GB Mac?
Computed with the open FitLLM engine — accurate per-layer KV-cache modeling, not a naive estimate. Updated 2026-07-10.
Memory breakdown (8-bit, F16 KV, 33K context)
| Model weights | 701 GB |
| KV cache | 2.7 GB |
| Runtime + macOS | 87.5 GB |
| Total used | 798 / 64 GB |
| Short by | 734 GB |
Max context at 8-bit: does not fit. Unified memory is shared by the OS — FitLLM leaves ~20% headroom.
Every quantization on M5 Max 64GB
| Quant | Weights | Fits (KV F16) | Used @32K |
|---|---|---|---|
| 4bit | 351 GB | ❌ won't fit | 405 / 64 GB |
| 8bit | 701 GB | ❌ won't fit | 798 / 64 GB |
| 16bit | 1403 GB | ❌ won't fit | 1583 / 64 GB |
Lower quants free memory at some output-quality cost — 4-bit is the common sweet spot for local use.
▶ Open the interactive calculator (this exact setup)Embed this verdict
Live badge for your README or model card — recomputed by the engine, never stale:
[](https://fitllm.run/can-i-run/glm-5-2-on-m5-max-64gb)
Or from your terminal (exit 0/1 — works as a pre-download guard):
npx fitllm "GLM-5.2" --mac 64Why most calculators get this wrong
GLM-5.2 uses MLA (Multi-head Latent Attention): K/V are compressed into a single low-rank latent (512 + 64 RoPE dims) shared across all heads — cached once, not per-head K and V. Naive "2 × heads × head_dim × layers" formulas over-count its KV cache by an order of magnitude.
Other options
same Mac Models that fit in 64GB: GLM-4.7-Flash, gpt-oss-20b, Qwen 3.6 27B, Qwen 3.6 35B-A3B, Qwen-AgentWorld-35B-A3B, Gemma 4 e2b, Gemma 4 e4b, Gemma 4 12b, Gemma 4 26b A4B, Gemma 4 31b, Llama-3.2-3B-Instruct, Llama-3.1-8B-Instruct, Qwen3-0.6B, Qwen3-1.7B, Llama-3.2-1B-Instruct, Gemma-3-1B-it.
Reproduce it
Open math: fitllm-engine (MIT), from official config.json.
All numbers are computed by the open-source fitllm-engine (MIT) from official model config.json values — reproduce or audit them yourself. Estimates; real usage varies with runtime (llama.cpp / MLX / Ollama), driver and display. Found a mismatch? Report it. · FitLLM home