MistralMixtral 8x7B Instruct on NVIDIA RTX PRO 6000 Blackwell Max-Q
Yes — RTX PRO 6000 Blackwell Max-Q runs Mixtral 8x7B Instruct excellently at Q5_K_M — 115 tok/s. 96 GB VRAM with plenty of headroom.
Model Size
46.7B
Device VRAM
96 GB
Bandwidth
1800 GB/s
Quantization
Q5_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Mixtral 8x7B Instruct on NVIDIA RTX PRO 6000 Blackwell Max-Q at Q5_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 115 tok/s | 42ms | ✓ Yes | Excellent | estimated |
Notes
Q5_K_M
96 GB GDDR7 fits Q5_K_M (31.4 GB) with 65 GB headroom. 1.8 TB/s bandwidth. High quality quantization with good speed.
About Mixtral 8x7B Instruct
Mixtral 8x7B Instruct (46.7B) is a chat, coding, reasoning, multi-purpose model. Mixture-of-Experts model: 46.7B total params but only ~12.9B active per token. Quality closer to a 13B dense model with inference speed to match. Needs more VRAM for the full weight set though.
View all Mixtral 8x7B Instruct hardware options →About NVIDIA RTX PRO 6000 Blackwell Max-Q
NVIDIA RTX PRO 6000 Blackwell Max-Q has 96 GB at 1800 GB/s. Street price: $7,000.
See all models NVIDIA RTX PRO 6000 Blackwell Max-Q can run →Estimate method: Estimated from full RTX PRO 6000 with ~8% reduction for Max-Q 300W power envelope. Reference hardware source: nvidia.com (2026-03-29)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.