← Back to community benchmarks
Qwen3.6-35B-A3Bmxfp8
Performance
64k
tokens
1,775
PP tok/s
52.4
TG tok/s
36914
TTFT (ms)
40.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,984 | 93.5 | 34.4 GB | view |
| 4k | 2,044 | 91.6 | 35.2 GB | view |
| 8k | 2,432 | 89.4 | 35.5 GB | view |
| 16k | 2,494 | 82.7 | 36.1 GB | view |
| 32k | 2,289 | 70.4 | 37.5 GB | view |
| 64k | 1,775 | 52.4 | 40.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 93.5 | 1.00× |
| 2× | 145.0 | 1.55× |
| 4× | 187.9 | 2.01× |