Configs › Qwen3.8-Flash-Next-REAP-288 › Qwen3.8-Flash-Next-REAP-288 on Mac Max: 52 tok/s, 3 measured configs
Qwen3.8-Flash-Next-REAP-288 on Mac Max: 52 tok/s, 3 measured configs
Measured Qwen3.8-Flash-Next-REAP-288 speeds on Mac Max: fastest 52 tok/s single-stream (MLX-4BIT, mlx (speculative decode, mtp)), 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 Qwen3.8-Flash-Next-REAP-288 on Mac Max: 52 tok/s (MLX-4BIT, mlx (speculative decode, mtp)), snapshot 2026-10-29.
Every measured single-stream run of Qwen3.8-Flash-Next-REAP-288 on Mac Max
| Decode tok/s | Quant | Backend | Context | Trust | Measured by | Source checked | Source |
|---|---|---|---|---|---|---|---|
| 52 | MLX-4BIT | mlx (speculative decode, mtp) | 10240 | Extracted, source-linked | 30cmtonyfaker | 2026-09-06 | source |
| 37 | MLX-4BIT | mlx/pmlx | Extracted, source-linked | sh0wie | 2026-08-29 | source | |
| 28 | MLX-4BIT | mlx | Extracted, source-linked | sh0wie | 2026-09-01 | source |
Backends on Mac Max
Fastest plain-decoding run per backend. Quants can differ between rows.
- mlx/pmlx: 37 tok/s (MLX-4BIT)
- mlx: 28 tok/s (MLX-4BIT)
Questions and answers
- How fast is Qwen3.8-Flash-Next-REAP-288 on Mac Max?
- The fastest of 3 measured configs is 52 tok/s single-stream (MLX-4BIT, mlx (speculative decode, mtp)). The slowest is 28 tok/s.
- Which backend is fastest for Qwen3.8-Flash-Next-REAP-288 on Mac Max?
- mlx/pmlx at 37 tok/s, then mlx at 28. Each backend figure is its best plain-decoding row and may use a different quant.
See also: Qwen3.8-Flash-Next-REAP-288 on every box · Mac Max hardware page (from S$3,499 in Singapore today).
Last updated: snapshot 2026-10-29; newest source check 2026-09-06.
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.