Dual RTX 5070 Ti on Ryzen 9 9900X (capy-flash maintainer rig)

Name: Dual RTX 5070 Ti on Ryzen 9 9900X (capy-flash maintainer rig)
Creator: RigBase
License: https://creativecommons.org/licenses/by/4.0/

GPU(s)	2x RTX 5070 Ti 16 GB Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)	32
CPU	AMD Ryzen 9 9900X (12 cores) Amazon · eBay (used) · Newegg
Motherboard
RAM	96 GB DDR5-5600 Amazon · eBay (used) · Newegg
PSU
Other	PCIe 5.0 x8+x8, no P2P; Ubuntu, CUDA 13.1
Reported total cost
Power

Measured speed (generation tokens/sec)

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

Model	Quant	Engine	tok/s	Details
Qwen3.8 Flash-Next	GSQ-RCO (64 GB edition)	capy-flash v0.7.0, 2 GPUs, agentic decode	182	📏 Maintainer/user decode tok/s from the capy-flash README
Qwen3.8 Flash-Next	NVFP4	capy-flash v0.6.0, 2 GPUs, agentic decode	155	📏 Maintainer/user decode tok/s from the capy-flash README
Qwen3.8 27B	3-bit GSQ	capy-flash (1 GPU), MTP, decode at 8k prompt	139	⚡ spec-decode (MTP)context: 8k prompt📏 Maintainer/user decode tok/s from the capy-flash README
Qwen3.8 27B	3-bit GSQ	capy-flash, 2 GPUs, MTP, decode at 8k prompt	230	⚡ spec-decode (MTP)context: 8k prompt📏 Maintainer/user decode tok/s from the capy-flash README

Benchmarks section of the capy-flash README, measured by the maintainer on his own machine. The README also lists LocalMaxxing reasoning-v1 prompt figures (234 tok/s Flash-Next 64 GB, 288 tok/s 27B on 2 GPUs), which are higher than the decode figures used here. Found via localmaxxing (discovery only); numbers re-checked at the original source on 2026-10-24.

Current GPU street price (estimate, not the builder's cost)

2× RTX 5070 Ti: ≈€1,188 each (≈$1,331), new, approx. price as of 2026-10-16, lowest listing on billiger.de (PNY GeForce RTX 5070 Ti 16 GB GDDR7)

Estimated GPU cost for this build today: ≈€2,375
New retail prices in Germany incl. VAT; used cards are often much cheaper. Prices change daily.

Source: https://github.com/ValerioDolci/capy-flash

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 2x RTX 5070 Ti run Qwen3.8 27B? · Can RTX 5070 Ti run Qwen3.8 27B? · Can 2x RTX 5070 Ti run Qwen3.8 Flash-Next?