Can I run Llama-3.1-8B-Instruct on a M5 Max 128GB Mac?
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 | 7.5 GB |
| KV cache | 4.0 GB |
| Runtime + macOS | 4.5 GB |
| Total used | 21.9 / 128 GB |
| Free | 106 GB |
Max context at 8-bit: ~131K tokens. 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 | 3.7 GB | ✅ up to 131K ctx | 17.8 / 128 GB |
| 8bit | 7.5 GB | ✅ up to 131K ctx | 21.9 / 128 GB |
| 16bit | 14.9 GB | ✅ up to 131K ctx | 30.3 / 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:
[](https://fitllm.run/can-i-run/llama-3-1-8b-instruct-on-m5-max-128gb)
Or from your terminal (exit 0/1 — works as a pre-download guard):
npx fitllm "Llama-3.1-8B-Instruct" --mac 128Why most calculators get this wrong
Llama-3.1-8B-Instruct's KV cache is computed per layer with its real head_dim and grouped-query head count — not the uniform "all layers × full context" shortcut most calculators use.
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