Yes — GPT-oss 120B (120B) runs at 7 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via Ollama. First token latency is 5.5s. OpenAI's 120B open-source model — high quality, needs 128 GB Mac.
LLMCheck measured GPT-oss 120B on M5 Max using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.
| Metric | Value |
|---|---|
| Tokens per second | 7 tok/s |
| Time to first token | 5.5s |
| Quantization | Q4_K_M |
| Minimum RAM | 128 GB |
| Recommended engine | Ollama |
| Parameters | 120B |
| Benchmark date | 2026-03 |
Q4_K_M 120B Ollama M5 Max
The recommended engine for GPT-oss 120B on M5 Max is Ollama. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~128 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M4 Ultra | 10 tok/s | 4.2s | 192 GB | MLX |
To run GPT-oss 120B on M5 Max you need:
See how GPT-oss 120B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard