← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4
Performance
32k
tokens
1,297
PP tok/s
71.4
TG tok/s
25266
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,376 | 111.1 | 19.9 GB | view |
| 4k | 1,707 | 105.7 | 20.7 GB | view |
| 8k | 1,705 | 94.7 | 21.1 GB | view |
| 16k | 1,576 | 86.6 | 21.7 GB | view |
| 32k | 1,297 | 71.4 | 23.0 GB | current |
| 64k | 1,001 | 32.4 | 25.7 GB | view |
| 128k | 633.3 | 17.7 | 31.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 111.1 | 1.00× |
| 2× | 175.0 | 1.58× |
| 4× | 241.6 | 2.17× |