Yes — Qwen 3.5 35B (35B) runs at 22 tok/s on M3 Max with 96 GB RAM using Q4_K_M quantization via Ollama. First token latency is 1.5s. Alibaba's 35B dense model for high-RAM Macs needing top-tier output.
LLMCheck measured Qwen 3.5 35B on M3 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 | 22 tok/s |
| Time to first token | 1.5s |
| Quantization | Q4_K_M |
| Minimum RAM | 96 GB |
| Recommended engine | Ollama |
| Parameters | 35B |
| Benchmark date | 2026-01 |
Q4_K_M 35B Ollama M3 Max
The recommended engine for Qwen 3.5 35B on M3 Max is Ollama. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~96 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 52 tok/s | 0.9s | 64 GB | MLX |
| M5 Max | 48 tok/s | 0.9s | 128 GB | Ollama |
| M4 Max | 34 tok/s | 1.2s | 48 GB | Ollama |
To run Qwen 3.5 35B on M3 Max you need:
See how Qwen 3.5 35B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard