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× RTX PRO 6000
GLM-5.3-Flash EXL3 with vLLM on 2× RTX PRO 6000: 152 tok/s according to huggingface.co (dataset as of Nov 3, 2026).
by brandonmusic
≤ 3 bit: quantization may cost quality
Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.
What matters before you rebuild it.
1 request, generation at 32K context (speed table; measured only as a path of four Sparks inside a ring of eight, not as a ring of four), thinking always on (measured before the profile default high, i.e. template default max), with MTP3 (per recipe) Source
1 request, prose prompt, with MTP + DFlash2 (per recipe) Source
Prose decode, 1 request; quality (FP8 KV, 4-bit dense): GSM8K 98.8% / HumanEval 95.7% / HumanEval+ & MBPP+ 86.5% Source
1 request, prose prompt, with MTP + DFlash2 (per recipe) Source
1 request, prose prompt, with DFlash2 (per recipe) Source
1 request, prose prompt, with DFlash2, TR3 weights (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.
