Mistral Nemo 12B cost & VRAM calculator

What does Mistral Nemo 12B 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

Provider	Rate ($/1M)	Monthly cost
Io Net	$0.02 in · $0.02 out · $0.01 cache	$0.0 cheapest
DekaLLM	$0.02 in · $0.03 out	$0.0 cheapest
DeepInfra	$0.03 in · $0.03 out	$0.0 cheapest
Parasail	$0.03 in · $0.03 out	$0.0 cheapest
Mistral	$0.15 in · $0.15 out · $0.02 cache	$0.0 cheapest

Monthly cost is an estimate from list prices and your workload - verify against the provider before committing. Cached fraction applies the cache rate to that share of input.

Can you run it locally?

YES - IT RUNS ON HARDWARE YOU CAN BUY

Mistral Nemo 12B 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 Q4_K_M

1009.4t/s

NVIDIA DGX Station 748GB 748GB Q4_K_M

602.6t/s

8x RTX 3090 rack (192GB) 192GB Q4_K_M

564.2t/s

4x RTX 5090 (128GB) 128GB Q4_K_M

539.9t/s

AMD Instinct MI300X (192GB) 192GB Q4_K_M

401.1t/s

4x RTX 4090 (96GB) 96GB Q4_K_M

303.7t/s

2x RTX 5090 (64GB) 64GB Q4_K_M

270.0t/s

2x RTX 3090 (48GB) 48GB Q4_K_M

141.0t/s

Single RTX 5090 (32GB) 32GB Q4_K_M

135.0t/s

RTX PRO 6000 Blackwell (96GB) 96GB Q4_K_M

135.0t/s

Mac Studio M4 Ultra 192GB 192GB Q4_K_M

89.7t/s

Mac Studio M4 Ultra 512GB 512GB Q4_K_M

89.7t/s

Single RTX 4090 (24GB) 24GB Q4_K_M

75.9t/s

MacBook Pro M5 Max 128GB 128GB Q4_K_M

50.5t/s

Single GTX 1080 Ti (11GB) 11GB Q4_K_M

36.5t/s

Dual EPYC 9004 + 768GB DDR5-4800 768GB Q4_K_M

34.7t/s

DGX Spark 128GB unified 128GB Q4_K_M

20.6t/s

Ryzen AI Max+ 395 128GB 128GB Q4_K_M

19.3t/s

Jetson AGX Orin 64GB 64GB Q4_K_M

15.4t/s

Epyc + 512GB DDR4-3200 + 2x RTX 3090 560GB Q4_K_M

15.4t/s

Epyc + 512GB DDR4-2400 + 2x RTX 3090 560GB Q4_K_M

11.6t/s

NVIDIA Jetson Orin NX 16GB 16GB Q4_K_M

7.7t/s

Q4_K_M

7.3GB weights 7.3GB min 8.5GB rec

Q8_0

13.2GB weights 13.2GB min 15.0GB 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