Yes — Qwen3.8-27B (27.8B) runs at 14 tok/s on M4 Pro with 48 GB RAM using Q4_K_M quantization via Ollama. A capable open-source LLM with 27.8B parameters.
Want to run Qwen3.8-27B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Qwen3.8-27B on M4 Pro 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 | 14 tok/s |
| Time to first token | — |
| Quantization | Q4_K_M |
| Minimum RAM | 48 GB |
| Recommended engine | Ollama |
| Parameters | 27.8B |
| Benchmark date | 2026-09 |
Q4_K_M 27.8B Ollama M4 Pro
The recommended engine for Qwen3.8-27B on M4 Pro is Ollama. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~48 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Ultra | 57 tok/s | — | 96 GB | MLX |
| M5 Max | 29 tok/s | — | 128 GB | MLX |
| M4 Max | 27 tok/s | — | 64 GB | MLX |
| M3 Max | 20 tok/s | — | 64 GB | MLX |
| M6 | 8 tok/s | — | 24 GB | MLX |
To run Qwen3.8-27B on M4 Pro you need:
Qwen3.8-27B needs about 48 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 Qwen3.8-27B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard