Intel's data center AI accelerator with on-chip Ethernet for cost-efficient scale-out.
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 Gaudi 2 has 96 GB of VRAM. In practice, that's enough memory for roughly 146B parameters at 4-bit or 38B 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) | Gaudi 2s needed | Cost /hr | Cost /mo |
|---|---|---|---|---|
Qwen3.8-27B
27B
|
18 GB
|
1
|
$1.16
|
$835
|
Gemma 4 31B
30.7B
|
22 GB
|
1
|
$1.16
|
$835
|
GPT-OSS-120B
117B · 5.1B active
|
67 GB
|
1
|
$1.16
|
$835
|
GLM-5.3-Flash
320B · 18B active
|
178 GB
|
8
|
$9.28
|
$6,682
|
MiniMax-M3
428B · 23B active
|
239 GB
|
8
|
$9.28
|
$6,682
|
DeepSeek V4.1 Flash
552B · 16B active
|
306 GB
|
8
|
$9.28
|
$6,682
|
Kimi K3
2.8T · 104B active
|
1,544 GB
|
18
|
–
|
–
|
Estimates based on the median on-demand rate. Memory is weights plus FP8 KV cache at 32K context per request (FP16/BF16 in the 16-bit column). 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.
Intel Gaudi 2 · Per GPU
| Compute · dense | |
|---|---|
| FP8 | 865 TFLOPS |
| FP16 / BF16 | 432 TFLOPS |
| Precision support | FP8FP16BF16TF32FP32INT8 |
| Memory | |
|---|---|
| Capacity | 96 GB HBM2e |
| Bandwidth | 2,450 GB/s |
| Silicon | |
|---|---|
| Architecture | Gaudi (2nd Gen) |
| Process | TSMC 7nm |
| Fabric and host | |
|---|---|
| GPU interconnect | RoCE 600 GB/s |
| Host interface | PCIe 4.0 x16 |
| Power | |
|---|---|
| Board power | 600 W |
Source: official Intel Gaudi 2 datasheet.
As of November 12, 2026, the median on-demand price is $1.16 per GPU per hour across 4 providers.
| Billing type | Configs | Median /GPU/hr | Cheapest |
|---|---|---|---|
On-demand | 7 | $1.16 | $1.05 (not verified in stock, Cyfuture AI) |
Reserved | 12 | $0.60 (12 mo, not verified in stock, Cyfuture AI) |
No median for reserved: we only show this when at least 3 providers list the GPU on that billing type.
The lowest listed on-demand price for the Gaudi 2 is $1.05 per GPU per hour from Cyfuture AI, though we haven't verified current stock. Cheapest verified in stock: on-demand $1.21 from Sesterce. Other billing types: reserved $0.60 (12 mo, not verified in stock), also from Cyfuture AI.
At 720 hours per month, one Gaudi 2 costs an estimated $835 at the median on-demand price. Cheapest verified in stock: $871 per month on-demand.
GetDeploying currently tracks Gaudi 2 configs from 4 providers. Sesterce and Runcrate have verified in-stock on-demand configs. See the full price comparison above for every provider and config.
One Gaudi 2 runs models up to roughly 146B parameters at 4-bit quantization or 38B 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.
Comes with 96GB HBM2e and 24x 100GbE RoCEv2 ports integrated on-chip, so clusters scale out over standard Ethernet without separate NICs. FP8 support and competitive pricing make it a cost-efficient option for training and inference on the Intel Gaudi software stack.
Last updated
