B300
NVIDIA
144GB VRAM · 4099 GB/s bandwidth · 1231.8 FP16 TFLOPS · 1400W TDP
The B300 has 144GB of VRAM with 4099 GB/s memory bandwidth and 1231.8 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (1127 tok/s), Qwen 2.5 7B (593 tok/s), Llama 3.1 8B (561 tok/s). Models larger than ~245B parameters won't fit even at Q4. Electricity cost is approximately $151/month at 1400W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 1127 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | comfortable | 593 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | comfortable | 561 tok/s |
| Mistral Small 24B | 24.0B | 12 GB | comfortable | 187 tok/s |
| Gemma 3 27B | 27.4B | 14 GB | comfortable | 164 tok/s |
| Qwen 2.5 Coder 32B | 32.5B | 16 GB | comfortable | 138 tok/s |
| Llama 3.3 70B | 70.6B | 35 GB | comfortable | 63 tok/s |
| Qwen 2.5 72B | 72.7B | 36 GB | comfortable | 62 tok/s |
| Llama 3.1 405B | 405B | 202 GB | won't fit | |
| DeepSeek R1 671B | 671B | 336 GB | won't fit |
Similar GPUs
| GPU | VRAM | BW | TFLOPS | TDP |
|---|---|---|---|---|
| H200 NVL | 141GB | 4890 GB/s | 241.3 | 600W |
| H200 SXM 141 GB | 141GB | 4890 GB/s | 267.6 | 700W |
| Radeon Instinct MI250 | 128GB | 3280 GB/s | 362.1 | 500W |
| Radeon Instinct MI250X | 128GB | 3280 GB/s | 383.0 | 500W |
| Radeon Instinct MI300 | 128GB | 6550 GB/s | 383.0 | 600W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.