Yes — Hunyuan Hy3 (295B-A21B) runs at 16 tok/s on M3 Ultra with 256 GB RAM using Q4_K_M quantization via LM Studio. First token latency is 0.9s. A capable open-source LLM with 295B-A21B parameters.
Want to run Hunyuan Hy3 faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Hunyuan Hy3 on M3 Ultra using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →
| Metric | Value |
|---|---|
| Tokens per second | 16 tok/s |
| Time to first token | 0.9s |
| Quantization | Q4_K_M |
| Minimum RAM | 256 GB |
| Recommended engine | LM Studio |
| Parameters | 295B-A21B |
| Benchmark date | 2026-08 |
Q4_K_M 295B-A21B LM Studio M3 Ultra
The recommended engine for Hunyuan Hy3 on M3 Ultra is LM Studio. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~256 GB) and start an interactive chat session.
To run Hunyuan Hy3 on M3 Ultra you need:
Hunyuan Hy3 needs about 256 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.
See how Hunyuan Hy3 stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard