More
Best rig by budgetRent before you buySubmit a buildNewsletterFree datasetAdvertise
Submit build

Builds / RTX Pro 6000 (Blackwell)

RTX PRO 6000: Qwen3.8 Flash-Next NVIDIA FP4 QAD on TensorFold Zig, 271.4 tok/s (Mia's AI Lab recipe)

Last updated:

Source: mia-ai.net ↗More source: mia-ai.net ↗More source: github.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
GPU(s)
RTX Pro 6000 (Blackwell)
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)
96
CPU
not stated
Motherboard
not stated
RAM
not stated
PSU
not stated
Other
not stated
Reported total cost
not stated
Power
400 W GPU power limit per card

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Qwen3.8 Flash-NextNVIDIA FP4 QAD + MTPTensorFold Zig, 1 stream271.47,246 @ 32k-token prompt
est. TTFT @8k ≈ 1.1 s (calculated from measured prefill)		⚡ spec-decode (MTP)context: 262k · up to 3 at once📏 Single-stream decode as published on Mia's AI Lab recipe card (Decode speed, one stream (RTX PRO 6000 at 400 W)). Peak throughput 503.7 tok/s ×3 streams, 400 W. Prefill is the README figure at the same 400 W limit (8,519.9 tok/s at the default 600 W). At 300 W the README lists 213.4 tok/s decode.

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.

Recipe and numbers by Mia's AI Lab (mia-ai.net), recipe last updated 2026-11-02; RigBase read the recipe card on 2026-11-03 and checked the decode figure against the recipe page. RigBase did not re-run it. Prefill is prompt-processing speed on a 32k prompt where listed.

Source: https://mia-ai.net/models/Qwen3.8-Flash-Next-RTX-PRO-6000-TernsorFold
https://mia-ai.net/models
https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-RTX-PRO-6000-TernsorFold

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/mia-rtx-pro-6000-qwen3-8-flash-next-rtx-pro-6000-ternsorfold.svg)](https://getrigbase.com/builds/mia-rtx-pro-6000-qwen3-8-flash-next-rtx-pro-6000-ternsorfold/)

HTML

<a href="https://getrigbase.com/builds/mia-rtx-pro-6000-qwen3-8-flash-next-rtx-pro-6000-ternsorfold/" rel="noopener"><img src="https://getrigbase.com/badge/mia-rtx-pro-6000-qwen3-8-flash-next-rtx-pro-6000-ternsorfold.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)

Quick answers: Can RTX Pro 6000 (Blackwell, 96 GB) run Qwen3.8 Flash-Next?