← All articles

#dgx-spark

3 articles

All articles tagged "dgx-spark" — self-hosted AI fixes, setups, and architecture notes.

Why hf download Lies to You at 22 GB on DGX Spark

Why hf download Lies to You at 22 GB on DGX Spark

The huggingface-hub CLI exits zero while leaving five out of six safetensor shards as .incomplete files. Three failure modes from the same model pull, and the wrapper that catches all of them.

Read article →
Qwen3.6-35B-A3B PrismaQuant at 95 tok/s on a single Spark (Spark Arena rank 4) beats my measured Mistral Small 4 at 35 tok/s by 2.7x on paper. This is the plan, not the result. SWE-Bench scores, opencode replacing vibe, why Mistral stays installed for creative prose, the Hacker News critiques on opencode I take seriously, and the two-day prep before day-2 measurements land on 2026-05-25.
strategy

Spark Arena Rank 4 Made Me Add Qwen3.6 to My DGX Spark

Qwen3.6-35B-A3B PrismaQuant at 95 tok/s on a single Spark (Spark Arena rank 4) beats my measured Mistral Small 4 at 35 tok/s by 2.7x on paper. This is the plan, not the result. SWE-Bench scores, opencode replacing vibe, why Mistral stays installed for creative prose, the Hacker News critiques on opencode I take seriously, and the two-day prep before day-2 measurements land on 2026-05-25.
What a DGX Spark actually draws from the wall, what that costs in Germany versus the US, how it compares to a lightbulb and a Bitcoin miner, and how many solar panels would offset it. With sources.
strategy

How Much Electricity Does Self-Hosted AI Actually Use? Lightbulbs, Bitcoin Miners, and Solar Panels

What a DGX Spark actually draws from the wall, what that costs in Germany versus the US, how it compares to a lightbulb and a Bitcoin miner, and how many solar panels would offset it. With sources.