Models / Mixtral 8x7B Instruct / Calculator

Mixtral 8x7B Instruct cost & VRAM calculator

What does Mixtral 8x7B Instruct cost to run for your workload, and can you run it on your own hardware? Set your workload below - we compute per-provider API cost live and tell you honestly whether local hardware can run it.

Your workload

Casual Power user Team of 5 Codebase task

API cost for your workload

No per-token API provider pricing tracked for Mixtral 8x7B Instruct yet. For flagship list prices, see the generic calculator.

Can you run it locally?

YES - IT RUNS ON HARDWARE YOU CAN BUY

Mixtral 8x7B Instruct fits on individual rigs. Here's the hardware that runs it comfortably; the full per-quant VRAM matrix and tok/s estimates live on the model page.

4x H100 80GB (320GB) 320GB Q3_K_M

1010.1t/s

NVIDIA DGX Station 748GB 748GB Q3_K_M

603.0t/s

8x RTX 3090 rack (192GB) 192GB Q3_K_M

564.6t/s

4x RTX 5090 (128GB) 128GB Q3_K_M

540.3t/s

AMD Instinct MI300X (192GB) 192GB Q3_K_M

401.4t/s

4x RTX 4090 (96GB) 96GB Q3_K_M

303.9t/s

2x RTX 5090 (64GB) 64GB Q3_K_M

270.2t/s

2x RTX 3090 (48GB) 48GB Q3_K_M

141.1t/s

Single RTX 5090 (32GB) 32GB Q3_K_M

135.1t/s

RTX PRO 6000 Blackwell (96GB) 96GB Q3_K_M

135.1t/s

Mac Studio M4 Ultra 192GB 192GB Q3_K_M

89.8t/s

Mac Studio M4 Ultra 512GB 512GB Q3_K_M

89.8t/s

Single RTX 4090 (24GB) 24GB Q3_K_M

76.0t/s

MacBook Pro M5 Max 128GB 128GB Q3_K_M

50.5t/s

Dual EPYC 9004 + 768GB DDR5-4800 768GB Q3_K_M

34.7t/s

DGX Spark 128GB unified 128GB Q3_K_M

20.6t/s

Ryzen AI Max+ 395 128GB 128GB Q3_K_M

19.3t/s

Jetson AGX Orin 64GB 64GB Q3_K_M

15.4t/s

Epyc + 512GB DDR4-3200 + 2x RTX 3090 560GB Q3_K_M

15.4t/s

Epyc + 512GB DDR4-2400 + 2x RTX 3090 560GB Q3_K_M

11.6t/s

Q3_K_M

19.0GB weights 19.0GB min 21.0GB rec

Q4_K_M

26.5GB weights 26.5GB min 28.3GB rec

Want the own-vs-rent payback (capex vs your monthly API bill)? The budget tool computes that against representative rigs.

Full model card API pricing table Generic token calculator