Yes — Qwen 3.5 9B (9B) runs at 26 tok/s on M6 with 16 GB RAM using Q4_K_M quantization via MLX. First token latency is Nones. Alibaba's 9B model — top pick for 8 GB and 16 GB Macs.
Want to run Qwen 3.5 9B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Qwen 3.5 9B on M6 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 | 26 tok/s |
| Time to first token | Nones |
| Quantization | Q4_K_M |
| Minimum RAM | 16 GB |
| Recommended engine | MLX |
| Parameters | 9B |
| Benchmark date | 2026-08 |
Q4_K_M 9B MLX M6
The recommended engine for Qwen 3.5 9B on M6 is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 82 tok/s | 0.5s | 64 GB | Ollama |
| M4 Pro | 40 tok/s | 0.4s | 24 GB | MLX |
| M4 | 18 tok/s | 0.6s | 16 GB | LM Studio |
| M3 | 15 tok/s | 0.7s | 16 GB | Ollama |
| M1 | 10 tok/s | 1.1s | 16 GB | Ollama |
To run Qwen 3.5 9B on M6 you need:
Qwen 3.5 9B needs about 16 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 Qwen 3.5 9B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard