Model benchmarks

ornith-1.0-9b local LLM performance

As of July 2026, ornith-1.0-9b runs at up to 62.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).

LM Studio

Model size

9B

Peak speed

62.5 tok/s

Average speed

60.8 tok/s

Min memory

8.9 GB

Max context

6,020 tokens

Best quality

86.9

Benchmark runs

2

GPUs tested

1

Performance by hardware and tool

Every hardware/tool/quantization combination ornith-1.0-9b has been benchmarked on, ranked by peak token generation speed. Last updated July 2026.

HardwareToolQuantBest tok/sAvg tok/sMemoryContextQualityRuns
NVIDIA GeForce RTX 4070 Ti SUPERLM Studio62.5 tok/s60.8 tok/s8.9 GB6,020 tokens73.22

Frequently asked questions

How fast is ornith-1.0-9b for local inference?
Across 2 community benchmark runs, ornith-1.0-9b reaches up to 62.5 tok/s and averages 60.8 tok/s, with the fastest results on NVIDIA GeForce RTX 4070 Ti SUPER.
How much memory does ornith-1.0-9b need?
The leanest observed configuration used about 8.9 GB of memory.
Which tools have been used to run ornith-1.0-9b?
Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.