GB300 cloud pricing, August 2026
Live GB300 quotes (288 GB VRAM) across the providers we track, cheapest first. Marketplace prices are real asks from the Vast.ai order book; secure/on-demand tiers carry datacenter SLAs (what the tiers mean).
Quotes refreshed 2026-08-23| Provider | Tier | $/hr per GPU | Median $/hr | Live offers | |
|---|---|---|---|---|---|
| Verda | spot | $4.31 | - | - | |
| Verda | on-demand | $8.62 | - | - |
What fits on a single GB300
Models from our tracked open-weight set that fit in 288 GB, with KV-cache headroom included. Bigger models need multi-GPU nodes (math in the calculator).
| Model | Params | Fits at | VRAM needed | Cheapest API $/1M out |
|---|---|---|---|---|
| GLM-4.7 Flash | 31B | FP8 | 43 GB | compare → |
| GLM-4.5 Air | 106B | FP8 | 146 GB | compare → |
| Qwen3.6 35B A3B | 36B | FP8 | 50 GB | compare → |
| Qwen3.6 27B | 27.8B | FP8 | 39 GB | compare → |
| Qwen3.5 35B A3B | 36B | FP8 | 50 GB | compare → |
| Qwen3.5 27B | 27.8B | FP8 | 39 GB | compare → |
| Qwen3 32B | 32.8B | FP8 | 46 GB | compare → |
| Qwen3 30B A3B | 30.5B | FP8 | 42 GB | compare → |
| Mistral Medium 3.5 | 128B | FP8 | 176 GB | compare → |
| Mistral Small 4 | 119.4B | FP8 | 165 GB | |
| Leanstral 1.5 | 119B | FP8 | 164 GB | |
| Mistral Small 3.1 | 24B | FP8 | 33 GB | |
| Nemotron 3 Super | 120B | FP8 | 165 GB | compare → |
| Nemotron 3 Nano | 30B | FP8 | 42 GB | compare → |
| IBM Granite 4.1 30B | 30B | FP8 | 42 GB | |
| IBM Granite 4.1 8B | 8.8B | FP8 | 13 GB | compare → |
| GPT-OSS 120B | 117B | FP8 | 161 GB | compare → |
| GPT-OSS 20B | 21B | FP8 | 29 GB | compare → |
| Llama 4 Scout | 109B | FP8 | 150 GB | compare → |
| Llama 3.3 70B | 70B | FP8 | 97 GB | compare → |
| Llama 3.1 8B | 8B | FP8 | 11 GB | compare → |
| Llama 3.2 3B | 3.2B | FP8 | 5 GB | compare → |
| Gemma 3 27B | 27B | FP8 | 38 GB | compare → |
| Gemma 3 12B | 12B | FP8 | 17 GB | compare → |
| Phi-4 | 14.7B | FP8 | 21 GB | compare → |
| Mixtral 8x7B | 46.7B | FP8 | 65 GB | compare → |
| DeepSeek R1 Distill Llama 70B | 70B | FP8 | 97 GB | compare → |
| DeepSeek R1 Distill Qwen 32B | 32.8B | FP8 | 46 GB | compare → |
| DeepSeek V4 Flash | 284B | INT4 | 196 GB | compare → |
| GLM-4.7 | 358B | INT4 | 247 GB | compare → |
| GLM-4.6 | 357B | INT4 | 246 GB | compare → |
| GLM-4.5 | 355B | INT4 | 245 GB | compare → |
| MiniMax M2.7 | 229B | INT4 | 158 GB | compare → |
| MiniMax M2.5 | 229B | INT4 | 158 GB | compare → |
| MiniMax M2.1 | 229B | INT4 | 158 GB | compare → |
| MiniMax M2 | 229B | INT4 | 158 GB | compare → |
| Qwen3.5 397B A17B | 397B | INT4 | 273 GB | compare → |
| Qwen3 235B A22B | 235B | INT4 | 162 GB | compare → |
| Llama 4 Maverick | 400B | INT4 | 276 GB | compare → |
| Llama 3.1 405B | 405B | INT4 | 279 GB | compare → |
FAQ
How much does it cost to rent a GB300?
As of 2026-08-23, GB300 rentals start at $4.31/hr (spot tier at Verda). Datacenter capacity with SLAs typically costs more than community or marketplace hardware.
What can you run on a GB300?
With 288 GB of VRAM, a single GB300 fits models up to roughly 205B parameters at FP8 or 411B at INT4 quantization, including KV-cache headroom.
Cite or embed today's floor
Live badge for a README. It updates itself with every daily refresh:
[](https://llmhosting.ai/gpus/gb300)
Citation: GB300 rental floor $4.31/hr (llmhosting.ai, 2026-08-23). Free to reuse with a link back.