RigBaseBuildsGPUsCan it run?GuidesBest rig for…By budgetRent before you buySubmit a buildNewsletterAdvertise

RTX 4090 (llm-speed signed run, Oct 2026): Flint 40B-A2.5B at 169-179 tok/s on llama.cpp

GPU(s)RTX 4090
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)24
CPUAMD EPYC 7452 (32 cores)
Amazon · eBay (used) · Newegg
Motherboard
RAM504 GB
Amazon · eBay (used) · Newegg
PSU
OtherServer host; llm-speed suite-v1 chat-short workload
Reported total cost
Power

Measured speed (generation tokens/sec)

📏 How measured: reported by the original source; RigBase re-checked the numbers at that source

ModelQuantEnginetok/sDetails
Flint 40B-A2.5BNVFP4llama.cpp 0.7.0-dev (build 11803)179.4
Flint 40B-A2.5BUD-Q3_K_XLllama.cpp 0.7.0-dev (build 11803)169.2

Signed community runs on llm-speed.com, 22 Oct 2026. NVFP4 run: https://llm-speed.com/r/r_0i0a9uq6fdx (chat-long 167.2 tok/s). Q3_K_XL run (16K context) chat-long: 157.8 tok/s.

Current GPU street price (estimate, not the builder's cost)Estimated GPU cost for this build today: ≈€3,955
New retail prices in Germany incl. VAT; used cards are often much cheaper. Prices change daily.

Source: https://llm-speed.com/r/r_sw92j6kg7js

Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

Quick answers: Can RTX 4090 run Flint 40B-A2.5B?