← Back to community benchmarks
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressivemxfp8
Performance
1k
tokens
1,709
PP tok/s
66.0
TG tok/s
599
TTFT (ms)
35.2
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.20
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,709 | 66.0 | 35.2 GB | current |
| 4k | 2,193 | 63.7 | 36.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.0 | 1.00× |
| 2× | 99.8 | 1.51× |
| 4× | 130.2 | 1.97× |