← Back to community benchmarks
Qwen3___5-35B-A3B9bit
Performance
4k
tokens
2,289
PP tok/s
75.5
TG tok/s
1790
TTFT (ms)
37.5
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 15.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,492 | 77.5 | 37.4 GB | view |
| 4k | 2,289 | 75.5 | 37.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 77.5 | 1.00× |
| 2× | 134.2 | 1.73× |
| 4× | 198.8 | 2.57× |