RTX Pro 6000 Blackwell Max-Q (300 W cap): Qwen3.8 27B on vLLM, NVFP4 vs BF16
| GPU(s) | RTX Pro 6000 Max-Q (Blackwell, 96 GB) Amazon · eBay (used) · Newegg |
|---|---|
| VRAM / unified memory (GB) | 96 |
| CPU | |
| Motherboard | |
| RAM | |
| PSU | |
| Other | CUDA 13.0; model on local XFS |
| Reported total cost | |
| Power | GPU power cap 300 W |
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 27B | NVFP4 (W4A16) + MTP (5 draft tokens), 256K context | vLLM 0.27.1 | 150 | ⚡ spec-decode (MTP) |
| Qwen3.8 27B | BF16 + MTP (5 draft tokens), 256K context | vLLM 0.20.1 | 85 | ⚡ spec-decode (MTP) |
Blog post of 17 Aug 2026. 'Raw' speed including hidden reasoning tokens; visible answer text ran at 84 (NVFP4) and 43 (BF16) tok/s. Max-Q is the 300 W blower variant of the RTX Pro 6000, so no street price is attached here.
Source: https://www.vaditaslim.com/blog/ai/qwen3.8-27b-two-rigs
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 RTX Pro 6000 Max-Q (Blackwell, 96 GB, 300 W) run Qwen3.8 27B?