Can I run Laguna XS 2.1 on a M6 32GB Mac?
Computed with the open FitLLM engine — accurate per-layer KV-cache modeling, not a naive estimate. Updated 2026-08-24.
Memory breakdown (8-bit, F16 KV, 33K context)
| Model weights | 31.1 GB |
| KV cache | 1.3 GB |
| Runtime + macOS | 13.4 GB |
| Total used | 45.9 / 32 GB |
| Short by | 13.9 GB |
Max context at 8-bit: does not fit. Unified memory is shared by the OS — FitLLM leaves ~20% headroom.
Every quantization on M6 32GB
| Quant | Weights | Fits (KV F16) | Used @32K |
|---|---|---|---|
| 4bit | 15.6 GB | ⚠️ won't fit | 28.4 / 32 GB |
| 8bit | 31.1 GB | ❌ won't fit | 45.9 / 32 GB |
| 16bit | 62.3 GB | ❌ won't fit | 80.8 / 32 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/laguna-xs-2-1-on-m6-32gb)
Or from your terminal (exit 0/1 — works as a pre-download guard):
npx fitllm "Laguna XS 2.1" --mac 32Why most calculators get this wrong
Laguna XS 2.1 interleaves sliding-window (local) and global attention 5:1. The local layers cap their KV cache at the 512-token window, and the global layers use a different head shape (head_dim 128 vs 128). A naive "all layers × full context × one head_dim" formula over-counts KV cache by several times.
Other options
same Mac Models that fit in 32GB: Gemma 4 e2b, Gemma 4 e4b, Gemma 4 12b, 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.
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