Can I run Qwen 3.8 27B on a M5 Pro 48GB 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 | 25.9 GB |
| KV cache | 2.0 GB |
| Linear-attention state (fixed — does not grow with context) | 0.1 GB |
| Runtime + macOS | 12.4 GB |
| Total used | 40.4 / 48 GB |
| Free | 7.6 GB |
Max context at 8-bit: ~13K tokens. Unified memory is shared by the OS — FitLLM leaves ~20% headroom.
Every quantization on M5 Pro 48GB
| Quant | Weights | Fits (KV F16) | Used @32K |
|---|---|---|---|
| 4bit | 12.9 GB | ✅ up to 157K ctx | 25.9 / 48 GB |
| 8bit | 25.9 GB | ⚠️ up to 13K ctx | 40.4 / 48 GB |
| 16bit | 51.7 GB | ❌ won't fit | 69.4 / 48 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/qwen-3-8-27b-on-m5-pro-48gb)
Or from your terminal (exit 0/1 — works as a pre-download guard):
npx fitllm "Qwen 3.8 27B" --mac 48Why most calculators get this wrong
Qwen 3.8 27B is a hybrid model: only 16 of its 64 layers use full attention — the rest are linear and keep no growing KV cache. Naive calculators count every layer at full context and badly over-estimate.
Other options
same Mac Models that fit in 48GB: gpt-oss-20b, Qwen 3.6 27B, Gemma 4 e2b, Gemma 4 e4b, Gemma 4 12b, Gemma 4 26b A4B, 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.
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