A100 variant with reduced interconnect for export-restricted markets.
Weekly median price per GPU per hour · Get the data
By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.
What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.
Within a group, five factors set the order:
We match the provider, its country, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
No providers match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price.
One A800 has 40 GB of VRAM. In practice, that's enough memory for roughly 47B parameters at 4-bit or 13B at 16-bit, assuming a 32K context. Below are some open-weight LLMs, with the estimated memory and GPUs each one needs.
| Model | Memory (INT4 / FP4) | A800s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
19 GB
|
1
|
–
|
–
|
Gemma 4 31B
30.7B
|
24 GB
|
1
|
–
|
–
|
GPT-OSS-120B
117B · 5.1B active
|
68 GB
|
2
|
–
|
–
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
5
|
–
|
–
|
MiniMax-M3
428B · 23B active
|
241 GB
|
7
|
–
|
–
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
9
|
–
|
–
|
Kimi K3
2.8T · 104B active
|
1,545 GB
|
43
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP16/BF16 KV cache at 32K context per request. GPU counts assume 90% of advertised VRAM is usable. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.
Nvidia A800 · Per GPU
| Compute · dense | |
|---|---|
| FP16 / BF16 | 312 TFLOPS 624 with sparsity |
| INT8 | 623.5 TOPS 1,247 with sparsity |
| FP32 | 19.5 TFLOPS |
| FP64 | 9.7 TFLOPS |
| Precision support | FP16BF16TF32FP32FP64INT4INT8 |
| Memory | |
|---|---|
| Capacity | 40 GB HBM2 |
| Bandwidth | 1,555 GB/s |
| Bus width | 5,120-bit |
| ECC | Yes |
| Silicon | |
|---|---|
| Architecture | Ampere |
| Process | TSMC N7 |
| Transistors | 54.2 billion |
| Shader cores | 6,912 CUDA cores |
| Matrix cores | 432 Tensor cores |
| Compute units | 108 SMs |
| Fabric and host | |
|---|---|
| GPU interconnect | NVLink 400 GB/s |
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 240 W |
| Cooling | Active |
| Platform | |
|---|---|
| Partitioning | MIG, up to 7 instances |
Source: official Nvidia A800 datasheet.
As of October 23, 2026, we track 4 configs from 1 provider. Prices are per GPU per hour.
| Billing type | Configs | Cheapest |
|---|---|---|
On-demand | 4 | $1.18 (not verified in stock, GPUhub) |
No median for on-demand: we only show this when at least 3 providers list the GPU on that billing type.
The lowest listed on-demand price for the A800 is $1.18 per GPU per hour from GPUhub, though we haven't verified current stock.
GetDeploying currently tracks A800 configs from 1 provider. See the full price comparison above for every provider and config.
One A800 runs models up to roughly 47B parameters at 4-bit quantization or 13B at 16-bit, assuming a 32K context. Larger models run across multiple GPUs: the model table above shows the estimated memory and GPU count for popular open-weight LLMs.
80GB HBM2e, similar to A100 but available in China. 400 GB/s NVLink supports multi-GPU configurations. Mature Ampere software compatibility.
Last updated
