1 request, decode at 16K context (record 2026-10-04), thinking on Source
- Custom kernel required
Your goal
Be visible where AI answers
Automate processes
Build a product
Put AI agents to work
Connect and modernize systems
Know where we stand
Use Cases
CRMStrengthen customer relationshipsPopularE-CommerceBoost online revenueBooking System24/7 appointment bookingProject ManagementCoordinate teamsInvoicingGet paid fasterAnalyticsData-driven decisionsLocal AI · Recipe · 2× DGX Spark
MiMo-V2.6-Flash-MOPD 309B-A15B with vLLM on 2× DGX Spark: 49 tok/s according to github.com (dataset as of Nov 3, 2026).
by myllmbox
1 request, code-heavy spec prompt (SQL/TypeScript), thinking off, with MTP K=3
Source: github.comEvery sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Shorter is better.
What matters before you rebuild it.
1 request, decode at 16K context (record 2026-10-04), thinking on Source
1 request, decode at 16K context (record 2026-10-04), thinking on Source
1 request, prose prompt, with MTP (per recipe) Source
1 request, prose prompt (long story), thinking off, with MTP Source
1 request, prose prompt, with MTP (per recipe) Source
1 request, generation at 32K context (speed table, pair), thinking on, xhigh, with MTP3 (per recipe) Source
In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.