Benchmarks · Measured, not quoted

Qwen3.8 27B on DGX Spark

These are our own measurements on our production hardware — the same machines serving api.axforge.ai. Every number carries its configuration and date; nothing here is a vendor quote.

Measured on production hardware 2026-08

Results

What we measured

SetupSingle-stream decode
Qwen3.8 27B (NVFP4) with multi-token-prediction speculative decoding15.9 tokens/s
Qwen3.8 27B (NVFP4), speculative decoding off5.8 tokens/s
Qwen3.6 35B A3B (MoE, ~3B active) — for comparison30.7 tokens/s
  • Measured on our production DGX Spark node, single-stream, 2026-08.

Methodology

Exactly how

HardwareNVIDIA DGX Spark — GB10 Grace-Blackwell, 128 GB unified memory. The production node, not a lab rig.
ModelQwen3.8 27B, NVFP4 quantization — the exact build served on the API.
Serving config65,536-token context, up to 4 concurrent sequences, vLLM-based serving with multi-token-prediction speculative decoding.
MeasurementSingle-stream decode throughput — tokens generated per second for one request.

Limitations

What we have not measured

We publish only what we measured: no time-to-first-token numbers, no concurrency curves, no third-party quality benchmarks — for model quality, see the model's official card. When we measure more, it lands here with the same labelling.

What it means

Reading the numbers

The MoE comparison shows the trade honestly: Qwen3.6 35B A3B decodes faster (fewer active parameters per token), Qwen3.8 27B is the stronger daily driver. Speculative decoding is why the dense model is usable single-stream — 2.7× over the baseline on the same silicon.

The same machine is rentable: DGX Spark, €495/month — or just call the model on the shared API from €0.29 / 1M input tokens.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms