Builds / 2x RTX Pro 6000 (Blackwell)
2x RTX PRO 6000: GLM-5.3 Flash EXL3 4-bit on TensorFold, 238.3 tok/s (Mia's AI Lab recipe)
- 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
- 300 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, 1 stream | 238.3 | 6,884 @ 32k-token prompt est. TTFT @8k ≈ 1.2 s (calculated from measured prefill) | ⚡ spec-decode (DFlash)context: 512K📏 Single-stream decode as published on Mia's AI Lab recipe card (Decode speed, one stream (2× RTX PRO 6000 at 300 W)). Peak throughput 448.7 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 2026-10-08; RigBase read the recipe card on 2026-10-27 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.
https://mia-ai.net/models
https://github.com/Aevonix/GLM-5.3-Flash-EXL3-2x-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.
Quick answers: Can 2x RTX Pro 6000 (Blackwell, 96 GB) run GLM-5.3 Flash?