← Back to community benchmarks
Qwen3.5-35B-A3B-Uncensored-FernflowerAI
Performance
1k
tokens
498.5
PP tok/s
55.3
TG tok/s
2054
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.5.dev2
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 498.5 | 55.3 | 35.4 GB | current |
| 4k | 590.4 | 52.5 | 36.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.3 | 1.00× |
| 2× | 83.0 | 1.50× |