NVIDIA B300 CC
288 GB HBM3e · Blackwell · 2,500 FP16 TFLOPS
Live NVIDIA B300 CC cloud prices from 1 provider, updated .
1 offering from 1 providers
| Provider | Per GPU / hour | Action | |
|---|---|---|---|
4 GPUs · $48.67 total | from$12.168 | Launch | |
| |||
NVIDIA B300 CC price history
The median NVIDIA B300 CC price is up 59% since August 17, 2026.
LLMs that fit on the NVIDIA B300 CC
Popular open-weight LLMs against 288 GB per GPU: weights plus room for the KV cache, at the best precision that fits. Showing the 12 largest that fit.
Runs on one NVIDIA B300 CC
- DeepSeek V4 Flash4-bit · 192 GB
- Solar Open2 250B4-bit · 192 GB
- Qwen3 235B-A22B4-bit · 181 GB
- Laguna-S 2.116-bit · 282 GB
- gpt-oss-120b4-bit · 78 GB
- Qwen3.6 35B-A3B16-bit · 86 GB
- Qwen3 32B16-bit · 79 GB
Needs more than one NVIDIA B300 CC
- Kimi K38 GPUs · 4-bit
- DeepSeek V4 Pro4 GPUs · 4-bit
- Kimi K2.54 GPUs · 4-bit
- GLM-5.24 GPUs · 8-bit
- DeepSeek R14 GPUs · 8-bit
Full table with every precision
Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 288 GB per GPU.
| Model | Parameters | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
| Kimi K3 Moonshot AI | 2.8T 104B active | — Not released | — Not released | 1,873 GB 8× · 431 GB free |
| DeepSeek V4 Pro DeepSeek | 1.6T 49B active | — Not released | — Not released | 1,038 GB 4× · 114 GB free |
| Kimi K2.5 Moonshot AI | 1T 32B active | — Not released | — Not released | 714 GB 4× · 438 GB free |
| GLM-5.2 Z.ai | 753B | 1,808 GB 8× · 496 GB free | 994 GB 4× · 158 GB free | 579 GB 4× · 573 GB free |
| DeepSeek R1 DeepSeek | 671B 37B active | — Not released | 826 GB 4× · 326 GB free | 481 GB 4× · 671 GB free |
| DeepSeek V4 Flash DeepSeek | 284B | — Not released | — Not released | 192 GB 1× · 96 GB free |
| Solar Open2 250B Upstage | 250B 15B active | 601 GB 4× · 551 GB free | 330 GB 4× · 822 GB free or 1× · 4% spare | 192 GB 1× · 96 GB free |
| Qwen3 235B-A22B Alibaba | 235B 22B active | 564 GB 4× · 588 GB free | 310 GB 4× · 842 GB free or 1× · 11% spare | 181 GB 1× · 107 GB free |
| Laguna-S 2.1 Poolside | 118B 8B active | 282 GB 1× · 5.8 GB free | 155 GB 1× · 133 GB free | 90 GB 1× · 198 GB free |
| gpt-oss-120b OpenAI | 117B 5.1B active | — Not released | — Not released | 78 GB 1× · 210 GB free |
| Qwen3.6 35B-A3B Alibaba | 35B 3B active | 86 GB 1× · 202 GB free | 47 GB 1× · 241 GB free | 28 GB 1× · 260 GB free |
| Qwen3 32B Alibaba | 32.8B | 79 GB 1× · 209 GB free | 43 GB 1× · 245 GB free | 25 GB 1× · 263 GB free |
Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput. How we estimate this · Start from a model instead
NVIDIA B300 CC specs
The NVIDIA B300 CC is an enterprise-class GPU built on the Blackwell architecture, featuring 288 GB of memory with 8,000 GB/s of memory bandwidth and a 1,400 W TDP. It delivers 75 TFLOPS of FP32 performance and 2,500 TFLOPS of FP16 tensor performance.
- Memory bandwidth
- 8,000 GB/s
- FP16 performance
- 2,500 TFLOPS
- peak
- FP32 performance
- 75 TFLOPS
- Architecture
- Blackwell
- TDP
- 1,400 W
- Brand
- NVIDIA
- Series
- B300