← Back to community benchmarks

Huihui-Qwen3.5-35B-A3B-abliterated-8bit

M4 Max (40c) · 64 GB · 8bit · 2026-03-10
Performance
1k
tokens
1,638
PP tok/s
85.3
TG tok/s
625
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,638 85.3 36.2 GB current
4k 1,733 81.7 36.3 GB view
Batching Results
Batch Size TG tok/s Speedup
85.3 1.00×
144.6 1.70×
207.3 2.43×
280.5 3.29×