Can I run GLM-4.7-Flash on a M5 Max 64GB Mac?

✅ Yes — it fits — up to ~135K tokens at 8-bit

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	27.9 GB
KV cache	1.7 GB
Runtime + macOS	6.6 GB
Total used	42.2 / 64 GB
Free	21.8 GB

Max context at 8-bit: ~135K tokens. 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	14.0 GB	✅ up to 203K ctx	26.5 / 64 GB
8bit	27.9 GB	✅ up to 135K ctx	42.2 / 64 GB
16bit	55.9 GB	❌ won't fit	73.5 / 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:

[![fits: GLM-4.7-Flash on M5 Max 64GB Mac](https://img.shields.io/endpoint?url=https%3A%2F%2Ffitllm.run%2Fapi%2Fbadge%3Fmodel%3DGLM-4.7-Flash%26ram%3D64%26quant%3D8)](https://fitllm.run/can-i-run/glm-4-7-flash-on-m5-max-64gb)

fit badge preview ← renders like this, live.

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

npx fitllm "GLM-4.7-Flash" --mac 64

Why most calculators get this wrong

GLM-4.7-Flash 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