Skip to main content

Instance Tiers

Choose the right GPU instance for your model size and performance needs.

Tier Overview

TierGPUVRAMPriceBest For
XS1x L424GB~$0.20/h7B-13B models
S1x L40S48GB~$0.60/h13B-34B models
M4x A10G96GB~$1.80/h30B-70B INT4
L4x L40S192GB~$3.50/h70B FP16
XL8x A100320-640GB~$12/h70B-180B
XXL8x H100/H200640-1128GB~$20/h405B

Tier XS - Entry Level

Best for small models (7B-13B parameters).

GPU XS

SpecValue
GPU1x NVIDIA L4
VRAM24GB
vCPUs4
RAM16GB
Storage250GB NVMe
Network10 Gbps
Price~$0.20/h
Recommended models: LLaMA 3.2 1B, Gemma 3 4B, Mistral 7B, LLaMA 3.1 8B

GPU XS (2x)

SpecValue
GPU1x NVIDIA L4
VRAM24GB
vCPUs8
RAM32GB
Storage450GB NVMe
Network15 Gbps
Price~$0.35/h

Tier S - Small Production

Best for medium models (13B-34B parameters).

GPU S

SpecValue
GPU1x NVIDIA L40S
VRAM48GB
vCPUs4
RAM16GB
Storage250GB NVMe
Network10 Gbps
Price~$0.60/h
Recommended models: LLaMA 3.1 13B, CodeLlama 13B, Llama 4 Scout 17B

GPU S (2x)

SpecValue
GPU1x NVIDIA L40S
VRAM48GB
vCPUs8
RAM32GB
Storage450GB NVMe
Network15 Gbps
Price~$1.00/h
Recommended models: CodeLlama 34B, Mixtral 8x7B, Qwen3 30B

Tier M - Medium Production

Best for large quantized models (30B-70B INT4).

GPU M

SpecValue
GPU4x NVIDIA A10G
VRAM96GB
vCPUs48
RAM192GB
Storage3.8TB NVMe
Network40 Gbps
Price~$1.80/h
Recommended models: LLaMA 3.1 70B (AWQ), Qwen2 72B (AWQ), DeepSeek 67B (AWQ)

GPU M (2x)

SpecValue
GPU4x NVIDIA A10G
VRAM96GB
vCPUs96
RAM384GB
Storage3.8TB NVMe
Network50 Gbps
Price~$3.00/h

GPU M (4x)

SpecValue
GPU8x NVIDIA A10G
VRAM192GB
vCPUs192
RAM768GB
Storage7.6TB NVMe
Network100 Gbps
Price~$5.00/h

Tier L - Large Production

Best for full-precision large models (70B FP16).

GPU L

SpecValue
GPU4x NVIDIA L40S
VRAM192GB
vCPUs48
RAM384GB
Storage3.8TB NVMe
Network40 Gbps
Price~$3.50/h
Recommended models: LLaMA 3.1 70B, Qwen2 72B, DeepSeek V3 70B

GPU L (2x)

SpecValue
GPU4x NVIDIA L40S
VRAM192GB
vCPUs96
RAM768GB
Storage3.8TB NVMe
Network50 Gbps
Price~$6.00/h
Recommended models: Mixtral 8x22B

GPU L (4x)

SpecValue
GPU8x NVIDIA L40S
VRAM384GB
vCPUs192
RAM1536GB
Storage7.6TB NVMe
Network100 Gbps
Price~$10.00/h

Tier XL - Enterprise

Best for very large models (70B-180B).

GPU XL

SpecValue
GPU8x NVIDIA A100 (40GB)
VRAM320GB
vCPUs96
RAM1152GB
Storage8TB NVMe
Network400 Gbps EFA
Price~$12.00/h
Recommended models: Falcon 180B, DeepSeek R1 180B

GPU XL (80GB)

SpecValue
GPU8x NVIDIA A100 (80GB)
VRAM640GB
vCPUs96
RAM1152GB
Storage8TB NVMe
Network400 Gbps EFA
Price~$18.00/h

Tier XXL - Colossal

Best for the largest models (405B).

GPU XXL

SpecValue
GPU8x NVIDIA H100 (80GB)
VRAM640GB
vCPUs192
RAM2048GB
Storage8TB NVMe
Network3200 Gbps EFA v2
Price~$20.00/h
Recommended models: LLaMA 3.1 405B (FP8), DBRX 132B

GPU XXL (H200)

SpecValue
GPU8x NVIDIA H200 (141GB)
VRAM1128GB
vCPUs192
RAM2048GB
Storage8TB NVMe
Network3200 Gbps EFA v2
Price~$30.00/h
Recommended models: LLaMA 3.1 405B (FP16)

Choosing the Right Tier

By Model Size

Model ParametersPrecisionRecommended Tier
1B - 8BFP16XS
7B - 13BINT4XS
13B - 30BFP16S
30B - 34BINT4/FP16S / S-2x
70BINT4/AWQM
70BFP16L
70B - 180BFP16XL
405BFP8XXL
405BFP16XXL-H200

By Use Case

Use CaseRecommended Tier
Development/TestingXS
Small productionS
Cost-optimized productionM (quantized)
High-quality productionL
Enterprise/Maximum qualityXL / XXL