← Back to community benchmarks
osmQwopus-3.6-27B-Coder-uncensored-MXFP8
Performance
1k
tokens
200.5
PP tok/s
13.3
TG tok/s
5108
TTFT (ms)
27.6
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.3
macOS
macOS 26.5.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 200.5 | 13.3 | 27.6 GB | current |
| 4k | 201.7 | 13.1 | 29.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.3 | 1.00× |
| 2× | 21.7 | 1.63× |
| 4× | 23.2 | 1.74× |