DGX Station (GB300)
NVIDIA DGX Station (GB300): 252 GB of memory at 7100 GB/s. Below: the open models it can run, estimated at 252 GB with an 8K context. 252 GB of HBM3e at 7.1 TB/s on one GPU, plus 496 GB of CPU memory: 280B-class MoE models fit in fast memory at 4-bit. Quote-only, and it needs a 20 A circuit.
Last updated: 2026-10-16
Specifications
What it can run
Best-quality quantization that fits with a 8K context, and the estimated generation speed. Estimates, not benchmarks. See the methodology.
| Model | Params | Best quant | Memory | tok/s (est.) |
|---|---|---|---|---|
| DeepSeek-V4-Flash | 284B (13B) | Q6_K | 229.3 GiB | 241 |
| Qwen3.8-Flash-Next | 180B (6B) | Q8_0 | 187.7 GiB | 305 |
| Qwen3.5-122B-A10B | 122B (10B) | FP16 | 239.3 GiB | 166 |
| Mistral Small 4 119B (2603) | 119B (6.5B) | FP16 | 233.4 GiB | 217 |
| gpt-oss-120b | 117B (5.1B) | FP16 | 229.6 GiB | 247 |
| Llama 4 Scout 17B-16E Instruct | 109B (17B) | FP16 | 215.2 GiB | 113 |
| GLM-4.5-Air | 106B (12B) | FP16 | 209.2 GiB | 146 |
| Qwen3-Coder-Next (80B-A3B) | 80B (3B) | FP16 | 157.1 GiB | 312 |
| Llama 3.3 70B Instruct | 70B | FP16 | 139.9 GiB | 33 |
| Qwen3.5-35B-A3B | 35B (3B) | FP16 | 69.1 GiB | 312 |
| Qwen3.6-35B-A3B | 35B (3B) | FP16 | 69.1 GiB | 312 |
| Qwen3-32B | 32.8B | FP16 | 66.6 GiB | 66 |
| DeepSeek-R1-Distill-Qwen-32B | 32.76B | FP16 | 66.6 GiB | 66 |
| Gemma 4 31B IT | 30.7B | FP16 | 61.6 GiB | 70 |
| Qwen3-30B-A3B (2507) | 30.5B (3.3B) | FP16 | 60.9 GiB | 300 |
| Qwen3-Coder-30B-A3B-Instruct | 30.5B (3.3B) | FP16 | 60.9 GiB | 300 |
| GLM-4.7-Flash (30B-A3B) | 30B (3B) | FP16 | 59.6 GiB | 312 |
| Qwen3.5-27B | 27B | FP16 | 53.8 GiB | 78 |
| Qwen3.6-27B | 27B | FP16 | 53.8 GiB | 78 |
| Qwen3.8-27B | 27B | FP16 | 53.8 GiB | 78 |
| Gemma 3 27B IT | 27B | FP16 | 54.3 GiB | 78 |
| Gemma 4 26B A4B IT | 25.2B (3.8B) | FP16 | 50.1 GiB | 283 |
| Mistral Small 3.2 24B Instruct (2506) | 24B | FP16 | 48.7 GiB | 86 |
| Magistral Small 1.2 (2509) | 24B | FP16 | 48.7 GiB | 86 |
| Devstral Small 2 24B Instruct (2512) | 24B | FP16 | 48.7 GiB | 86 |
| gpt-oss-20b | 21B (3.6B) | FP16 | 41.8 GiB | 290 |
| Phi-4 (14B) | 14B | FP16 | 29.4 GiB | 131 |
| Gemma 3 12B IT | 12B | FP16 | 24.8 GiB | 146 |
| Gemma 4 12B Unified IT | 11.95B | FP16 | 24.2 GiB | 147 |
| Qwen3.5-9B | 9B | FP16 | 18.4 GiB | 178 |
| Qwen3-8B | 8.2B | FP16 | 17.7 GiB | 189 |
| DeepSeek-R1-0528-Qwen3-8B | 8.19B | FP16 | 17.6 GiB | 189 |
| Llama 3.1 8B Instruct | 8B | FP16 | 17.1 GiB | 192 |
| Gemma 4 E4B IT | 8B | FP16 | 16.4 GiB | 192 |
| Llama 3.2 3B Instruct | 3.21B | FP16 | 7.7 GiB | 304 |
| Kimi K2.6 | 1000B (32B) | Doesn't fit | – | – |
| DeepSeek-R1-0528 (671B) | 671B (37B) | Doesn't fit | – | – |
Prices
No prices recorded for this device yet. All prices →
Frequently asked questions
Which LLMs can the DGX Station (GB300) run?
With 252 GB and an 8K context, the largest models that fit include: DeepSeek-V4-Flash, Qwen3.8-Flash-Next, Qwen3.5-122B-A10B, Mistral Small 4 119B (2603), gpt-oss-120b. See the full table below.
How fast is the DGX Station (GB300) for local LLMs?
Generation speed is mostly set by memory bandwidth (7100 GB/s). For Llama 3.1 8B Instruct at FP16, expect roughly 192 tokens/s; bigger models are slower.
Can the DGX Station (GB300) run 70B models?
Yes. Llama 3.3 70B Instruct fits on the DGX Station (GB300) (252 GB) at FP16 with an 8K context, using about 139.9 GiB, at an estimated 33 tokens/s.