Tokenstead Weekly
The 10-minute AI week
Keeping up with AI now requires being unemployed. Or a 10-minute read every
morning. We send the second one.
Oct 12 - Oct 18, 2026
Generated 2026-10-24 22:11 UTC
/
Permalink
Past issues archive
Tokenstead Weekly: keep up with AI in 10 minutes a day. What shipped, what it
means for people who run AI on their own hardware. Read it over coffee.
Sends automatically to confirmed subscribers every Monday at 6:47am via Resend.
Copy as plain text if you want to paste it elsewhere.
Subscribe free
New guides
The runtimes catalog now carries 21 verified local inference engines. The pick-by-hardware map: GGUF, Metal, GPU serving, NPU specialists.
/guides/local-inference-engines
China's Announcement 48 draft adds 23 AI technologies to export review, but published weights are exempt. What 2T and top-10 thresholds mean for open models.
/guides/china-open-weight-export
RTX Spark laptops ship October 16 with Hermes Agent on the launch slide, pickable in Windows' agent setup flow, running Qwen 3.8 27B local on 128GB.
/guides/hermes-rtx-spark
New open-weight models
1048k context
/models/muse-wonder
384k context
/models/subq-snap
1024k context, 3 quants
/models/muse-spark-open-816b
Cloud prices - current snapshot
Current per-token pricing from the OpenRouter sync. Week-over-week price deltas coming when we add price history.
current per-token pricing snapshot
/models/kimi-k3
current per-token pricing snapshot
/models/deepseek-v4-pro
New rigs this week
512GB unified
/rigs/niklas-lenz-spark-rack
Featured this week
1024GB unified
/rigs/u5mcxttb
96GB unified
/rigs/e6dcoht6
512GB unified
/rigs/niklas-lenz-spark-rack
Tokenstead Weekly - Oct 12-18, 2026
## New guides
- Twenty-one ways to run a model locally: the engine catalog
/guides/local-inference-engines
The runtimes catalog now carries 21 verified local inference engines. The pick-by-hardware map: GGUF, Metal, GPU serving, NPU specialists.
- China's export draft leaves published weights alone
/guides/china-open-weight-export
China's Announcement 48 draft adds 23 AI technologies to export review, but published weights are exempt. What 2T and top-10 thresholds mean for open models.
- Hermes Agent ships on NVIDIA's RTX Spark launch
/guides/hermes-rtx-spark
RTX Spark laptops ship October 16 with Hermes Agent on the launch slide, pickable in Windows' agent setup flow, running Qwen 3.8 27B local on 128GB.
## New open-weight models
- Muse Wonder
/models/muse-wonder
1048k context
- SubQ Snap
/models/subq-snap
384k context
- Muse Spark Open 816B-A42B
/models/muse-spark-open-816b
1024k context, 3 quants
## Cloud prices - current snapshot
Current per-token pricing from the OpenRouter sync. Week-over-week price deltas coming when we add price history.
- Kimi K3 - cheapest: Relace $0.30/M input
/models/kimi-k3
current per-token pricing snapshot
- DeepSeek V4 Pro - cheapest: Nous Portal $0.53/M input
/models/deepseek-v4-pro
current per-token pricing snapshot
## New rigs this week
- 4x DGX Spark 15U rack - Niklas
/rigs/niklas-lenz-spark-rack
512GB unified
## Featured this week
- 8x DGX Spark rack by FPGA des GARÇONS
/rigs/u5mcxttb
1024GB unified
- Theo's 4x Mac Mini cluster
/rigs/e6dcoht6
96GB unified
- 4x DGX Spark 15U rack - Niklas
/rigs/niklas-lenz-spark-rack
512GB unified
Tokenstead is an open community catalog that helps you run AI on hardware you own.
The weekly digest is the 10-minute version of keeping up.
Subscribe at /subscribe.