1 request, prose prompt (sampled, thinking off), with LiLiCorr (per recipe) Source
- ≤ 3 bit: quantization may cost quality
- Custom kernel required
- License unclear
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 · 1× DGX Spark
Nemotron-3.5-Super-VL 120B-A12B NVFP4 with vLLM on 1× DGX Spark: 48 tok/s according to github.com (dataset as of Nov 3, 2026).
by sfxnz
1 request, mixed prompt set (SPEED-Bench), greedy, thinking off, with LiLiCorr (per recipe)
Source: github.comEvery sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
Sums over all streams are marked; per request it is correspondingly less.
Shorter is better.
What matters before you rebuild it.
1 request, prose prompt (sampled, thinking off), with LiLiCorr (per recipe) Source
1 request, prose prompt (essay), context 2k, no drafter (per recipe) Source
1 request, chat prompt (20 prompts, thinking off), no drafting (default profile) Source
1 request, prose prompt, with DFlash2 (per recipe) Source
1 request, prose prompt, with MTP (per recipe) Source
1 request, prose prompt, with MTP (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.