← Back to community benchmarks

Qwen3.6-35B-A3B-Holo3-Qwopus-mxfp4

M4 (10c) · 32 GB · 4bit · 2026-04-24
Performance
1k
tokens
416.1
PP tok/s
49.7
TG tok/s
2461
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 416.1 49.7 18.2 GB current
4k 457.2 47.0 18.9 GB view
8k 443.6 43.9 19.2 GB view
16k 408.3 37.4 19.9 GB view
32k 338.6 28.6 21.2 GB view
Batching Results
Batch Size TG tok/s Speedup
49.7 1.00×
74.2 1.49×
88.7 1.78×