Nvidia A800 80G mieten.

Name: Nvidia A800 80G
Brand: Nvidia
SKU: nvidia-a800-80g

Ampere 80GB VRAM From $1.19/hr

Per hour

$1.19

Per day

$28.56

Per week

$199.92

Per month

$857

Price history

Daily median across providers.

Where to rent it

All providers carrying this GPU.

Provider	$/hr	Range	Offers	30d trend	Updated
CloudGPU	$1.19/hr	$1.19/hr–$1.19/hr	81	↑ 4%	about 5 hours	Launch ↗Empfehlung

AI models that fit See all 233 →

Run these on this GPU.

Kimi K2.7 Code 8× · int4
Ling-2.6-1T 8× · int4
Ring-2.6-1T 8× · int4

AI models

Models that run on this GPU.

Open-Weights-Modelle, die für Inferenz auf diese Karte passen, mit der kleinsten Kartenzahl und der Genauigkeit, mit der jedes geladen wird. Täglich aus der Modellgröße und dem Kartenspeicher berechnet. Die 60 größten von 233 passenden Modellen.

Renting for inference?

Pair these models with the cheapest provider on the rental table. See rental rates on the Overview tab →

FAQ

AI models on this GPU.

What AI models can I run on a Nvidia A800 80G?

The list above shows open-weights models whose memory need fits this card: on one card when the model uses at least a quarter of its 80 GB, or on 2, 4 or 8 of them when it is too large for one. Each row gives the fewest cards and the precision (FP16, FP8 or INT4) that load it.

What's the VRAM minimum to run a model on the Nvidia A800 80G?

We count the weights (parameters × bytes per weight: FP16 = 2, FP8 = 1, INT4 = 0.5), add the KV cache for an 8K-token context, and add 15% for the runtime. A model fits when that is within 90% of the cards' memory. A 70B model needs about 164 GB at FP16 and about 43 GB at INT4. A longer context needs more.

How does quantization (FP16 vs FP8 vs INT4) affect what fits?

Lower-precision quantization shrinks the memory footprint nearly linearly with the bit count. The trade-off is output quality: FP16 is the reference, FP8 is usually indistinguishable for most prompts, INT8 introduces small quality losses, INT4 is noticeably degraded on reasoning-heavy tasks but fine for chat. The badge on each row tells you which level the recommendation assumes.

Can I fine-tune on the Nvidia A800 80G or only do inference?

The rows here are for inference. Full fine-tuning needs several times more memory than inference at the same model size, because gradients, optimizer state and activations all live in memory. LoRA and QLoRA cut that a lot. The fine-tune cost tool sizes a run for you.

How are these GPU counts worked out?

We compute them every day from the model's parameter count and the card's memory, with the formula above. They are estimates, not tests we ran. Tokens per second, where shown, is an estimate from the card's memory bandwidth on one card.

Nvidia A800 80G mieten.

Daily median across providers.

All providers carrying this GPU.

Run these on this GPU.

Models that run on this GPU.

Kimi K2.7 Code

Ling-2.6-1T

Ring-2.6-1T

MiMo-V2.6-Pro

MiMo-V2.5-Pro

Kimi K2.6

Kimi K2.5

Kimi K2 Thinking

Kimi K2

Kimi K2 0905

Inkling FP4

Muse Spark Open

Hy4 preview

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash 1017

GLM-5

GLM-5.1

glm-5.3

GLM 5.2

DeepSeek V3.2

DeepSeek V3.1 Terminus

DeepSeek V3 0324

DeepSeek V3.2 Speciale

DeepSeek-V3.1

DeepSeek V3.1 Nex N1

Cogito v2.1 671B

DeepSeek V3.2 Exp

DeepSeek V3

R1 0528

DeepSeek R1

Step 5 Preview

Nemotron 3 Ultra

Beam 1.0 501B A23B

Qwen3 Coder 480B A35B

Minimax M1 80K

MiniMax-Text-01

MiniMax M1

MiniMax M3

ERNIE 4.5 VL 424B A47B

Hermes 4 405B

Llama 3.1 405B

Hermes 3 405B Instruct

Llama 4 Maverick

Trinity Large Thinking

Qwen3.5 397B A17B

Nex-N2.5-Pro

Nex-N2-Pro

Hunyuan-Large

GLM-4.7

GLM-4.6

GLM-4.5

GLM 5.3 Flash

MiMo-V2.5

MiMo-V2.6-Flash

MiMo-V2-Flash

DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash 0731

ERNIE 4.5 300B A47B

Hy3

Hy3 preview

AI models on this GPU.