Can I run GLM-4.7-Flash on a M5 Ultra 256GB Mac?
Computed with the open FitLLM engine — accurate per-layer KV-cache modeling, not a naive estimate. Updated 2026-10-19.
Conditions: 8-bit · KV cache F16 · 32K context · macOS reserve (8.0 GB).
Memory breakdown (8-bit, F16 KV, 32K context)
| Model weights | 29.1 GB |
| KV cache | 1.7 GB |
| Runtime + macOS | 12.7 GB |
| Total used | 43.4 / 256 GB |
| Free | 213 GB |
Context at 8-bit: recommended max ~198K tokens (keeps 20% headroom) · hard limit ~198K tokens. Unified memory is shared with macOS and your apps — the recommended max leaves 20% of it free.
Every quantization on M5 Ultra 256GB
| Quant | Weights | Recommended max ctx | Hard limit | Used @32K |
|---|---|---|---|---|
| 4bit | 14.5 GB | ~198K | ~198K | ✅ 27.2 / 256 GB |
| 8bit | 29.1 GB | ~198K | ~198K | ✅ 43.4 / 256 GB |
| 16bit | 58.1 GB | ~198K | ~198K | ✅ 76.0 / 256 GB |
Recommended max = the longest context that still keeps the 20% headroom macOS needs · hard limit = the longest that fits at all (KV cache F16).
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 at exactly these conditions, never stale:
[](https://fitllm.run/can-i-run/glm-4-7-flash-on-m5-ultra-256gb)
Or from your terminal (exit 0/1 — works as a pre-download guard):
npx fitllm "GLM-4.7-Flash" --mac 256 --quant 8 --ctx 32768 --kv 16Why 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 256GB: GLM-4.7-Flash, gpt-oss-20b, gpt-oss-120b, 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, MiniCPM5-1B, Qwen3-0.6B, Qwen3-1.7B, Llama-3.2-1B-Instruct, Gemma-3-1B-it, Qwen 3.8 27B, Laguna XS 2.1, Laguna S 2.1, Spark-X2.5-4B, Granite-4.2-30B, MiniCPM5-2B, Nex-N2.5-mini.
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