Builds / 2x RTX Pro 6000 (Blackwell)

2x RTX PRO 6000: GLM-5.3 Flash EXL3 4-bit on TensorFold Zig, 245.5 tok/s (Mia's AI Lab recipe)

Last updated: 2 Nov 2026

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): 2x RTX Pro 6000 (Blackwell)
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB): 192
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)

Model	Quant	Engine	tok/s	Prompt processing (tok/s)	Details
GLM-5.3 Flash	EXL3 4-bit + DFlash2	TensorFold Zig, 1 stream	245.5	6,033 @ 32k-token prompt est. TTFT @8k ≈ 1.4 s (calculated from measured prefill)	⚡ spec-decode (DFlash)context: up to 1M📏 Single-stream decode as published on Mia's AI Lab recipe card (Decode speed, one stream (2× RTX PRO 6000 at 400 W)). Peak throughput 436.6 tok/s ×4 streams.

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 2026-11-01; RigBase read the recipe card on 2026-11-02 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/GLM-5.3-Flash-2x-RTX-PRO-6000-TensorFold
https://mia-ai.net/models
https://github.com/MiaAI-Lab/GLM-5.3-Flash-2x-RTX-PRO-6000-TensorFold

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-2x-rtx-pro-6000-glm-5-3-flash-2x-rtx-pro-6000-tensorfold.svg)](https://getrigbase.com/builds/mia-2x-rtx-pro-6000-glm-5-3-flash-2x-rtx-pro-6000-tensorfold/)

HTML

<a href="https://getrigbase.com/builds/mia-2x-rtx-pro-6000-glm-5-3-flash-2x-rtx-pro-6000-tensorfold/" rel="noopener"><img src="https://getrigbase.com/badge/mia-2x-rtx-pro-6000-glm-5-3-flash-2x-rtx-pro-6000-tensorfold.svg" alt="Measured on RigBase" height="20"/></a>

Preview: · 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 2x RTX Pro 6000 (Blackwell, 96 GB) run GLM-5.3 Flash?