TensorQuaySGContact usContact

THE TENSORQUAY BLOG · LAB NOTES

Local AI.
Put to the test.

What fits, what finishes, what breaks. Experiments with open models and GPUs, from our team in Singapore. The settings and the awkward results come with the good ones.

LAB NOTE 04 · LONG SESSIONSTESTED

Eight long sessions.
64 GB of RAM.

The Qwen cache test again, on our own RTX 5090 test machine with the RAM budget of a TQ–32. Eight sessions with 32K of history averaged 33–36 tok/s per user over two runs. Why three of eight users were slower, and what happened when the cache spilled onto an SSD.

Read the long-session results
8 × 32K sessions · 1 × RTX 5090 · 64 GB-class RAM
Qwen3.8-27B NVFP4 · vLLM 0.28 · 24 GiB CPU KV tier
Mean per user · run 1 / run 233.1 / 35.1 tok/s
Slowest 3 of 8 usersabout 22–23 tok/s

First repeat of each run; scale 0–50 tok/s. Synthetic prompts and 128-token replies. Not an assembled TQ–32.

LAB NOTE 01 · CODING AGENTSTESTED

Qwen on one 5090.
Keep the history in the test.

7.0–7.6 → 35.8–44.1 effective tok/s per session · 2 repeats each

Four scripted 32K sessions, 24 GiB of CPU cache and two repeats. Warm follow-up turns exposed a limit that short prompts missed. Plus recordings of the separate coding-agent runs.

Read the Qwen benchmark

Enough detail to
question the result.

Each note separates the measured result from our interpretation, names the test configuration and explains what remains untested. Summary data is downloadable. Historical GPU test systems are described in each article; their results do not qualify an assembled workstation. Start with the local AI guides if you are new to running models.