/hub/runs/nova-rkllm-npu
Published result2026-04-10Indiedroid Nova

Indiedroid Nova RKLLM NPU Test

Three W8A8 RKLLM models ran on the RK3588S NPU with NPU utilization and memory monitored over SSH.

This page keeps the shared controls, retained measurements, failures, and comparison limits together. The linked files are there when you need the underlying table or method.

Comparison boundary

The three Nova rows share the local test. Raspberry Pi numbers in the article came from outside references with different runtime and quantization.

Recorded results

Open the details under any row for the specific setup, outcome, artifact identity, and supporting file.

Model and artifactRuntime and modeGenerationPromptPeakState
DeepSeek-R1 Distill Qwen 1.5B
W8A8 RKLLM
RKLLM 1.2.1
NPU · 50 state-capitals prompt
11.5 tok/sn/an/aPublished result
Open result details

Why this model is here

The Nova NPU run started at 11.5 tok/s, then the state-capitals answer degraded into invented cities.

It is the clearest example in the Hub of why throughput and useful output cannot be treated as the same result.

What ran

W8A8 RKLLM ran through RKLLM 1.2.1 using NPU in 50 state-capitals prompt mode on Indiedroid Nova.

Started fast, then invented cities around state seven.

Recorded setup

The full test page contains the shared controls and comparison boundary for this row.

Qwen 2.5 3B Instruct
W8A8 RKLLM
RKLLM 1.2.1
NPU · 50 state-capitals prompt
7 tok/sn/an/aPublished result
Open result details

Why this model is here

The Nova NPU result reached 7.0 tok/s and returned all 50 state capitals correctly.

It was slower than the smaller DeepSeek row but produced the useful answer on the shared prompt.

What ran

W8A8 RKLLM ran through RKLLM 1.2.1 using NPU in 50 state-capitals prompt mode on Indiedroid Nova.

Returned all 50 state capitals correctly.

Recorded setup

The full test page contains the shared controls and comparison boundary for this row.

Llama 3.1 8B Instruct
W8A8 RKLLM
RKLLM 1.2.1
NPU · 50 state-capitals prompt
3.72 tok/sn/an/aPublished result
Open result details

Why this model is here

The Nova NPU measured 3.72 tok/s. A separate 1.99 tok/s Pi 5 value remains labeled as an outside reference.

It connects Trevor-measured Nova data with a clearly separated published Pi reference without presenting the two methods as a matched hardware contest.

What ran

W8A8 RKLLM ran through RKLLM 1.2.1 using NPU in 50 state-capitals prompt mode on Indiedroid Nova.

Measured Nova NPU result.

Recorded setup

The full test page contains the shared controls and comparison boundary for this row.

Controls

  • Debian 12
  • RKLLM 1.2.1
  • NPU driver 0.9.7
  • W8A8 community model conversions
  • Shared 50 state-capitals prompt

What this run established

  • $DeepSeek 1.5B was fastest but began inventing cities.
  • $Qwen 2.5 3B returned all 50 state capitals correctly.
  • $The test shows why throughput and useful output need separate fields.

© 2026 Trevor Unland. All rights reserved.

RSS Feed

$ echo "Built with React + TypeScript"