Configs › Qwen3-30B-A3B tok/s: Mac Max 148.5, Strix Halo 79.1
Qwen3-30B-A3B tok/s: Mac Max 148.5, Strix Halo 79.1
Measured Qwen3-30B-A3B speeds: 148.5 tok/s on Mac Max (Q4_K_M, llama.cpp); 79.1 tok/s on Strix Halo. 3 configs, each linked to its source, snapshot 2026-10-16.
Snapshot 2026-10-16 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Quick answers
- How fast is Qwen3-30B-A3B on Mac Max?
- 148.5 tok/s single-stream decode (Q4_K_M, llama.cpp), the fastest of 2 measured configs on Apple M-series Max (MacBook Pro / Mac Studio Max), measured by emihiggins, source last checked 2026-09-29. source
- How fast is Qwen3-30B-A3B on Strix Halo?
- 79.1 tok/s single-stream decode (UD-Q4_K_XL, llama.cpp/rocm), the only measured config on AMD Strix Halo (Ryzen AI Max+ 395), measured by lhl, source last checked 2026-10-16. source
Measured configs for Qwen3-30B-A3B
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Qwen3-30B-A3B | Mac Max | Q4_K_M | llama.cpp | 148.5 tok/s (prefill 3497) | 512 | Extracted, source-linked | source |
| Qwen3-30B-A3B | Mac Max | MLX-4BIT | mlx | 147.2 tok/s (prefill 3458) | 512 | Extracted, source-linked | source |
| Qwen3-30B-A3B | Strix Halo | UD-Q4_K_XL | llama.cpp/rocm | 79.1 tok/s (prefill 687.9) | Structured table | source |
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.