Yes — Qwen3.8-Flash-Next (125B-A6B) runs at 49 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via MLX. A capable open-source LLM with 125B-A6B parameters.
Want to run Qwen3.8-Flash-Next faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Qwen3.8-Flash-Next on M5 Max 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 | 49 tok/s |
| Time to first token | — |
| Quantization | Q4_K_M |
| Minimum RAM | 128 GB |
| Recommended engine | MLX |
| Parameters | 125B-A6B |
| Benchmark date | 2026-09 |
Q4_K_M 125B-A6B MLX M5 Max
The recommended engine for Qwen3.8-Flash-Next on M5 Max 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 Ultra | 85 tok/s | — | 256 GB | MLX |
| M4 Ultra | 78 tok/s | — | 192 GB | MLX |
| M3 Ultra | 63 tok/s | — | 256 GB | MLX |
| M4 Max | 45 tok/s | — | 128 GB | MLX |
To run Qwen3.8-Flash-Next on M5 Max you need:
Qwen3.8-Flash-Next needs about 128 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-Flash-Next stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard