Can I run Hy3 on a M3 Ultra 512GB Mac?

Q: Can I run Hy3 on a M3 Ultra 512GB Mac?

Yes — Hy3 fits in 512 GB of M3 Ultra unified memory at 8-bit, with up to about 236K tokens of context. Computed from the model's official config.json by the open-source FitLLM engine.

✅ Yes — it fits — up to ~236K tokens at 8-bit

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	278 GB
KV cache	10.0 GB
Runtime + macOS	43.9 GB
Total used	332 / 512 GB
Free	180 GB

Max context at 8-bit: ~236K tokens. Unified memory is shared by the OS — FitLLM leaves ~20% headroom.

Every quantization on M3 Ultra 512GB

Quant	Weights	Fits (KV F16)	Used @32K
4bit	139 GB	✅ up to 262K ctx	176 / 512 GB
8bit	278 GB	✅ up to 236K ctx	332 / 512 GB
16bit	557 GB	❌ won't fit	644 / 512 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: Hy3 on M3 Ultra 512GB Mac](https://img.shields.io/endpoint?url=https%3A%2F%2Ffitllm.run%2Fapi%2Fbadge%3Fmodel%3DHy3%26ram%3D512%26quant%3D8)](https://fitllm.run/can-i-run/hy3-on-m3-ultra-512gb)

fit badge preview ← renders like this, live.

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

npx fitllm "Hy3" --mac 512

Why most calculators get this wrong

Hy3 is a Mixture-of-Experts: ~21B of 298.8B parameters are active per token, but all 298.8B must sit in memory. Naive calculators that size memory off active params (or KV off all layers) get this wrong.

Other options

same Mac Models that fit in 512GB: 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, Hy3, Qwen 3.8 27B, Laguna XS 2.1, Laguna S 2.1.

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