More
Submit build

Builds / RTX 5090 (400 W) + RTX 5060 Ti 16GB (180 W, peer expert tier

RTX 5090 + RTX 5060 Ti, 128 GB RAM: Qwen3.8 Flash-Next on Basalt 0.2.0 at 307 tok/s prose (NVFP4), 342 at UD-IQ3_XXS

Last updated:

Source: huggingface.co ↗More source: github.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
GPU(s)
RTX 5090 (400 W) + RTX 5060 Ti 16GB (180 W, peer expert tier)
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)
48
CPU
not stated
Motherboard
not stated
RAM
128 GB
Amazon · eBay (used) · Newegg
PSU
not stated
Other
Linux, Basalt 0.2.0 (MIT, a fork of Strata), int8 KV, experts that do not fit in VRAM in system RAM; MTP drafting on by default (output identical to plain decoding)
Reported total cost
not stated
Power
RTX 5090 capped at 400 W, RTX 5060 Ti at 180 W

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Qwen3.8 Flash-NextNVFP4-DQ6_K Basalt pack (NVIDIA NVFP4 experts, Q6_K dense, 122.0 GiB)Basalt 0.2.03077,807 @ 16K-token prompt
est. TTFT @8k ≈ 1.0 s (calculated from measured prefill)
⚡ spec-decode (MTP)context: single stream, prose📏 Engine author's best measured single-stream speed: prose 307, structured output 601, chat 335 tok/s; numbers move with every release
Qwen3.8 Flash-NextUnsloth UD-IQ4_XS Basalt pack (90.9 GiB)Basalt 0.2.0300not stated⚡ spec-decode (MTP)context: single stream, prose📏 Best measured: prose 300, structured 608, chat 363 tok/s
Qwen3.8 Flash-NextUnsloth UD-IQ3_XXS Basalt pack (81.6 GiB)Basalt 0.2.0342not stated⚡ spec-decode (MTP)context: single stream, prose📏 Best measured: prose 342, structured 658, chat 399 tok/s
Qwen3.8 Flash-NextQ8_0 Basalt pack (Unsloth, 178.3 GiB)Basalt 0.2.0112not stated⚡ spec-decode (MTP)context: single stream, prose📏 Best measured: prose 112, structured 166, chat 101 tok/s (most experts in RAM)

Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 ÷ prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.

Engine author's own numbers (jesdga95, Hugging Face pack card updated 8 Nov 2026; precision docs on GitHub). These are best measured speeds, not averages. Quality from the same card (100 wikitext-2 chunks vs a llama.cpp BF16 reference): NVFP4-DQ6_K KLD 0.0624 / 91.65% same top-1, UD-IQ4_XS 0.0818 / 90.52%, UD-IQ3_XXS 0.1188 / 88.67%, Q8_0 0.0200 / 95.34% (llama.cpp's Q8_0 scores 0.0325 / 93.98%).

Source: https://huggingface.co/jesdga/Qwen3.8-Flash-Next-Basalt
https://github.com/jesdga95/basalt/blob/main/docs/precision/qwen38-flash-next.md

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

Embed this result

Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds — numbers stay on the build page.

Markdown

[![Measured on RigBase](https://getrigbase.com/badge/rtx-5090-plus-5060-ti-128gb-qwen38-flash-next-basalt-020.svg)](https://getrigbase.com/builds/rtx-5090-plus-5060-ti-128gb-qwen38-flash-next-basalt-020/)

HTML

<a href="https://getrigbase.com/builds/rtx-5090-plus-5060-ti-128gb-qwen38-flash-next-basalt-020/" rel="noopener"><img src="https://getrigbase.com/badge/rtx-5090-plus-5060-ti-128gb-qwen38-flash-next-basalt-020.svg" alt="Measured on RigBase" height="20"/></a>

Preview: Measured on RigBase · How to use

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)

Speculative-decoding rows on this page are not like-for-like with plain decode. See how much MTP and DFlash really speed things up (measured pairs).