datacenter
Thuê Nvidia B300.
Blackwell
288GB VRAM
From $6.73/hr
Per hour
$6.73
Per day
$161.52
Per week
$1130.64
Per month
$4846
Provider spread
4 providers ·
up to 41% cheaper at the low end
Cheapest · $6.73/hr on io.net
Median $7.17/hr
Most expensive · $11.37/hr on Spheron Network
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
AI models that fit
See all 18 →
Run these on this GPU.
- MiniMax-Text-01 1× · int4
- Command R+ 1× · fp16
- GLM-4.5-Air 1× · fp16
Cloud instances
See all 17 →
Hyperscaler bundles.
Pre-configured on 4 clouds — from $7.40/hr total
($7.40/hr per GPU).
FAQ
Frequently asked.
How much does it cost to rent the Nvidia B300 right now?
The cheapest current listing is $6.73/hr on io.net, and the median across the 4 providers listing it is $7.40/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $4,913.
What AI models can the Nvidia B300 run?
With 288 GB it holds a 70B model at INT8/FP8 (about 70 GB of weights) on one card, or at 4-bit with plenty of room for long contexts and many concurrent requests. It can QLoRA fine-tune 70B models. FP16 70B (about 140 GB) needs two cards.
Which models are recommended for the Nvidia B300?
8 models in our catalog have a recommended configuration for this card, with the quantization that fits its 288 GB — see the AI models tab.
Why does the Nvidia B300 cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia B300 price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
Cloud instance options
Pre-configured instances on hyperscalers.
Whole-instance bundles (GPU + vCPU + RAM + disk) on the major clouds. Per-GPU rate often drops as the count rises. View = spec page · Launch = sign up (affiliate).
Cheapest bundle
$7.40/hr
Lowest $/hr per GPU
$7.40/hr
Providers
4
Instance shapes
17
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| on-demand · B300 | 1× | 28 | 240 GB | — | $7.40/hr | $7.40/hr | ||
| on-demand · B300 | 1× | 28 | 240 GB | — | $7.40/hr | $7.40/hr | ||
| on-demand · B300 | 1× | 28 | 240 GB | — | $7.40/hr | $7.40/hr | ||
| 1x B300_SXM6 | 1× | 30 | 255 GB | 500 GB | $11.37/hr | $11.37/hr | ||
| 1x B300_SXM6 | 1× | 30 | 255 GB | 500 GB | $11.37/hr | $11.37/hr | ||
| 1x B300_SXM6 | 1× | 30 | 255 GB | 500 GB | $11.37/hr | $11.37/hr | ||
| 1x B300_SXM6 | 1× | 30 | 255 GB | 500 GB | $11.37/hr | $11.37/hr | ||
| 1x B300_SXM6 | 1× | 30 | 255 GB | 500 GB | $11.37/hr | $11.37/hr | ||
| 1x B300_SXM6 | 1× | 24 | 346 GB | 512 GB | $12.42/hr | $12.42/hr | ||
| 1x B300_SXM6 | 1× | 24 | 346 GB | 512 GB | $12.42/hr | $12.42/hr | ||
| 1x B300_SXM6 | 1× | 24 | 346 GB | 512 GB | $12.42/hr | $12.42/hr | ||
| BM.GPU.B300.8 | 8× | — | — | — | $120.00/hr | $15.00/hr | ||
| BM.GPU.B300.8 | 8× | — | — | — | $120.00/hr | $15.00/hr | ||
| BM.GPU.B300.8 | 8× | — | — | — | $120.00/hr | $15.00/hr | ||
| p6-b300.48xlarge | 8× | — | — | — | $142.42/hr | $17.80/hr | ||
| p6-b300.48xlarge | 8× | — | — | — | $142.42/hr | $17.80/hr | ||
| p6-b300.48xlarge | 8× | — | — | — | $142.42/hr | $17.80/hr |
Looking for the cheapest rate?
Hyperscaler bundles include managed networking + SLAs. Raw per-GPU rental on P2P marketplaces is typically 3–10× cheaper.
See raw rental rates on the Overview tab →
FAQ
Cloud instances — common questions.
How much does it cost to rent the Nvidia B300 right now?
The cheapest current listing is $6.73/hr on io.net, and the median across the 4 providers listing it is $7.40/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $4,913.
What AI models can the Nvidia B300 run?
With 288 GB it holds a 70B model at INT8/FP8 (about 70 GB of weights) on one card, or at 4-bit with plenty of room for long contexts and many concurrent requests. It can QLoRA fine-tune 70B models. FP16 70B (about 140 GB) needs two cards.
Which models are recommended for the Nvidia B300?
8 models in our catalog have a recommended configuration for this card, with the quantization that fits its 288 GB — see the AI models tab.
Why does the Nvidia B300 cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia B300 price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
AI models
INT4
FP16
FP16
INT4
INT4
INT4
FP16
FP16
FP16
FP16
FP16
INT4
INT4
FP8
FP8
FP8
FP8
FP8
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia B300.
MiniMax-Text-01
by MiniMax
Required GPUs
1× Nvidia B300
Total VRAM
288 GB
Parameters
456B (46B active)
Context
4M tokens
Command R+
by Cohere
Required GPUs
1× Nvidia B300
Total VRAM
288 GB
Parameters
104B
Context
128K tokens
GLM-4.5-Air
by Zhipu AI
Required GPUs
1× Nvidia B300
Total VRAM
288 GB
Parameters
106B (12B active)
Context
128K tokens
MiniMax: MiniMax M2
by MiniMax
Required GPUs
1× Nvidia B300
Total VRAM
288 GB
Parameters
456B
Context
205K tokens
MiniMax: MiniMax M1
by MiniMax
Required GPUs
1× Nvidia B300
Total VRAM
288 GB
Parameters
456B
Context
1M tokens
MiniMax M2.7
by MiniMax
Required GPUs
1× Nvidia B300
Total VRAM
288 GB
Parameters
456B
Context
197K tokens
MiniMax-Text-01
by MiniMax
Required GPUs
4× Nvidia B300
Total VRAM
1152 GB
Parameters
456B (46B active)
Context
4M tokens
Baidu: ERNIE 4.5 VL 424B A47B
by Baidu
Required GPUs
4× Nvidia B300
Total VRAM
1152 GB
Parameters
424B
Context
131K tokens
MiniMax: MiniMax M2
by MiniMax
Required GPUs
4× Nvidia B300
Total VRAM
1152 GB
Parameters
456B
Context
205K tokens
MiniMax: MiniMax M1
by MiniMax
Required GPUs
4× Nvidia B300
Total VRAM
1152 GB
Parameters
456B
Context
1M tokens
MiniMax M2.7
by MiniMax
Required GPUs
4× Nvidia B300
Total VRAM
1152 GB
Parameters
456B
Context
197K tokens
Baidu: ERNIE 4.5 VL 424B A47B
by Baidu
Required GPUs
1× Nvidia B300
Total VRAM
288 GB
Parameters
424B
Context
131K tokens
Llama 3.1 405B
by Meta AI
Required GPUs
1× Nvidia B300
Total VRAM
288 GB
Parameters
405B
Context
128K tokens
MiniMax-Text-01
by MiniMax
Required GPUs
2× Nvidia B300
Total VRAM
576 GB
Parameters
456B (46B active)
Context
4M tokens
Baidu: ERNIE 4.5 VL 424B A47B
by Baidu
Required GPUs
2× Nvidia B300
Total VRAM
576 GB
Parameters
424B
Context
131K tokens
MiniMax: MiniMax M2
by MiniMax
Required GPUs
2× Nvidia B300
Total VRAM
576 GB
Parameters
456B
Context
205K tokens
MiniMax: MiniMax M1
by MiniMax
Required GPUs
2× Nvidia B300
Total VRAM
576 GB
Parameters
456B
Context
1M tokens
MiniMax M2.7
by MiniMax
Required GPUs
2× Nvidia B300
Total VRAM
576 GB
Parameters
456B
Context
197K tokens
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.
How much does it cost to rent the Nvidia B300 right now?
The cheapest current listing is $6.73/hr on io.net, and the median across the 4 providers listing it is $7.40/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $4,913.
What AI models can the Nvidia B300 run?
With 288 GB it holds a 70B model at INT8/FP8 (about 70 GB of weights) on one card, or at 4-bit with plenty of room for long contexts and many concurrent requests. It can QLoRA fine-tune 70B models. FP16 70B (about 140 GB) needs two cards.
Which models are recommended for the Nvidia B300?
8 models in our catalog have a recommended configuration for this card, with the quantization that fits its 288 GB — see the AI models tab.
Why does the Nvidia B300 cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia B300 price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.