Model benchmarks
Ornith-1.5-35B-A3B-oQ4e-mtp local LLM performance
As of August 2026, Ornith-1.5-35B-A3B-oQ4e-mtp runs at up to 113.4 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
oMLX
Model size
35B
Peak speed
113.4 tok/s
Average speed
111.8 tok/s
Min memory
20.8 GB
Max context
262,144 tokens
Avg output / run
40,822 tokens
Avg runtime / run
5m 49s
Avg quality
85.3
Benchmark runs
2
GPUs tested
1
Performance by hardware and tool
Every hardware/tool/quantization combination Ornith-1.5-35B-A3B-oQ4e-mtp has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Max | oMLX | — | 113.4 tok/s | 111.8 tok/s | 20.8 GB | 262,144 tokens | 85.3 | 2 |
Frequently asked questions
- How fast is Ornith-1.5-35B-A3B-oQ4e-mtp for local inference?
- Across 2 community benchmark runs, Ornith-1.5-35B-A3B-oQ4e-mtp reaches up to 113.4 tok/s and averages 111.8 tok/s, with the fastest results on Apple M5 Max.
- How much memory does Ornith-1.5-35B-A3B-oQ4e-mtp need?
- The leanest observed configuration used about 20.8 GB of memory.
- Which tools have been used to run Ornith-1.5-35B-A3B-oQ4e-mtp?
- Benchmarks were submitted using oMLX. Results are community-contributed and updated as new runs arrive.