RTX Spark on Surface Laptop runs Qwen 27B at 20.7 tok/s in Extended benchmark
draginol · x · 2026-10-19
Blogger draginol benchmarked local LLMs on the NVIDIA RTX Spark N1X (6144-core Blackwell GPU, 64GB RAM) inside a Surface Laptop, using the tougher Extended-mode benchmark.
The screenshot shows Qwen3.8 27B Q4KM (Locama GGUF, 35K context) results:
- Prefill: 644 tok/s at 8K context
- Decode: 20.7 tok/s
- First token: 1.73s with a 1K prompt
- Accuracy: 4/5 tasks passed
He also tested Gemma 12B and plans to publish a full roundup soon.
Related event: RTX Spark Tested: Runs 27B Models Locally, Beats Gaming Laptops(4 posts)→
More from Infra
- Elon Musk mocks what it's like trying to rent AI compute today — elonmusk · 2026-10-19
- New blog series part 1: a visual introduction to tensor core arithmetic — akbirthko · 2026-10-19
- Weekly recap: five vendors ship agent controls at five layers, desk-side AI draws most readers — shashib · 2026-10-19
- Hugging Face kicks off Open Source AI Week with ExecuTorch edge-AI hackathon — Thom_Wolf · 2026-10-19
- Local models are now good enough for first-round code review, dev finds while paying frontier API prices — draginol · 2026-10-19
- Dev replaces hundreds/month in Modal sandboxes with an idle Mac Mini at home — andersonbcdefg · 2026-10-19