Configs › Qwen3.6-35B-A3B › Qwen3.6-35B-A3B on Mac Max: 151.1 tok/s, 3 measured configs
Qwen3.6-35B-A3B on Mac Max: 151.1 tok/s, 3 measured configs
Measured Qwen3.6-35B-A3B speeds on Mac Max: fastest 151.1 tok/s single-stream (MLX-4BIT, mlx), 3 configs with quant, backend and context, each linked to its source, snapshot 2026-10-29.
Snapshot 2026-10-29 · 413 configs on AI boxes and 288 on GPU cards · 121 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.
Fastest measured single-stream run of Qwen3.6-35B-A3B on Mac Max: 151.1 tok/s (MLX-4BIT, mlx), snapshot 2026-10-29.
Every measured single-stream run of Qwen3.6-35B-A3B on Mac Max
| Decode tok/s | Quant | Backend | Context | Trust | Measured by | Source checked | Source |
|---|---|---|---|---|---|---|---|
| 151.1 | MLX-4BIT | mlx | 512 | Extracted, source-linked | emihiggins | 2026-09-29 | source |
| 124.3 | Q4_K_M | llama.cpp | 512 | Extracted, source-linked | emihiggins | 2026-09-29 | source |
| 30.8 | BF16 | mlx | Extracted, source-linked | lizhun781021 | 2026-09-29 | source |
Best quant on Mac Max
Fastest plain-decoding run per quant, versus the fastest quant.
- MLX-4BIT: 151.1 tok/s, fastest (mlx)
- Q4_K_M: 124.3 tok/s, 18% lower (llama.cpp)
- BF16: 30.8 tok/s, 80% lower (mlx)
Backends on Mac Max
Fastest plain-decoding run per backend. Quants can differ between rows.
- mlx: 151.1 tok/s (MLX-4BIT)
- llama.cpp: 124.3 tok/s (Q4_K_M)
Qwen3.6-35B-A3B on other boxes
- Strix Halo: 127.1 tok/s best of 29 configs
- Mac Ultra: 109.1 tok/s best of 1 config
- DGX Spark: 77.4 tok/s best of 22 configs
Questions and answers
- How fast is Qwen3.6-35B-A3B on Mac Max?
- The fastest of 3 measured configs is 151.1 tok/s single-stream (MLX-4BIT, mlx). The slowest is 30.8 tok/s.
- Which quant of Qwen3.6-35B-A3B is fastest on Mac Max?
- MLX-4BIT at 151.1 tok/s, ahead of Q4_K_M at 124.3, BF16 at 30.8. Plain decoding only.
- Which backend is fastest for Qwen3.6-35B-A3B on Mac Max?
- mlx at 151.1 tok/s, then llama.cpp at 124.3. Each backend figure is its best plain-decoding row and may use a different quant.
- How does Mac Max compare with other boxes for Qwen3.6-35B-A3B?
- Mac Max best 151.1 tok/s. Other boxes, best measured: Strix Halo 127.1, Mac Ultra 109.1, DGX Spark 77.4. Backends and quants differ, so this is the best known number per box, not a controlled test.
See also: Qwen3.6-35B-A3B on every box · Mac Max hardware page (from S$3,499 in Singapore today).
Last updated: snapshot 2026-10-29; newest source check 2026-09-29.
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.