Can I run GLM-5.2 on a M5 Max 128GB Mac?

❌ No — GLM-5.2 (8-bit) needs 798 GB of 128 GB unified memory

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 / 128 GB
Short by	670 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 128GB

Quant	Weights	Fits (KV F16)	Used @32K
4bit	351 GB	❌ won't fit	405 / 128 GB
8bit	701 GB	❌ won't fit	798 / 128 GB
16bit	1403 GB	❌ won't fit	1583 / 128 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:

[![fits: GLM-5.2 on M5 Max 128GB Mac](https://img.shields.io/endpoint?url=https%3A%2F%2Ffitllm.run%2Fapi%2Fbadge%3Fmodel%3DGLM-5.2%26ram%3D128%26quant%3D8)](https://fitllm.run/can-i-run/glm-5-2-on-m5-max-128gb)

fit badge preview ← renders like this, live.

Or from your terminal (exit 0/1 — works as a pre-download guard):

npx fitllm "GLM-5.2" --mac 128

Why 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 128GB: 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