llamaperf
Submit

Qwen3.8 27B

on M4 16GB · turboquant-mlx 0.24.0 / mlx-vlm 0.6.3

Apple hardware
Oct 11, 2026
Share
Throughput
3.6 t/s gen · 21.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
TurboQuant 3-bit g64 + 4-bit affine extras (MLX)
System RAM
16 GB

Summary

User reports Qwen3.8 27B at 3.6 t/s generation and 21 t/s prefill on an M4 Mac mini with 16 GB unified memory. Setup is turboquant-mlx 0.24.0 with TurboQuant 3-bit g64 weights and 4-bit affine embeddings, lm_head and vision tower, at a 2014-token prompt with 13.14 GiB measured peak. The source's four rows span 220 to 5017 prompt tokens, with decode 3.6 to 3.9 t/s and prefill 19.0 to 21.0 t/s; generated-token counts and KV precision are unstated.