The V100 SXM2 features 16 GB of memory.
Cheapest
—
No current offerings
Median
—
across 0 offerings
Most expensive
—
90-day trend
0.0%
median rate
Hardware specifications
Same across all providers
Market price history
Median price across all providers
Prices updated 5 hours ago
0 offerings from 0 providers
Sorted by price ascending. Compare configurations side-by-side.
| Provider | Count | vCPU | RAM | Region | Per GPU hour | Total/hr | Action |
|---|---|---|---|---|---|---|---|
| Try broadening your filters or clear all filters to start over. | |||||||
LLMs that fit on the V100 SXM2
Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 16 GB per GPU.
| Model | Parameters | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
| Mistral Small 3.2 24B Mistral AI | 24B | 58 GB Too large | 32 GB Too large | 18 GB Tight on 1× · 4% spare |
| gpt-oss-20b OpenAI | 21B 3.6B active | — Not released | — Not released | 17 GB Tight on 1× · 16% spare |
| Gemma 3 12B Google | 12.2B | 29 GB Too large | 16 GB Tight on 1× · 19% spare | 9.4 GB 1× · 6.6 GB free |
| Granite 4.1 8B IBM | 8.8B | 21 GB Too large | 12 GB 1× · 4.4 GB free | 6.8 GB 1× · 9.2 GB free |
| Qwen3 8B Alibaba | 8.2B | 20 GB Too large | 11 GB 1× · 5.2 GB free | 6.3 GB 1× · 9.7 GB free |
| Llama 3.1 8B Instruct Meta | 8B | 19 GB Too large | 11 GB 1× · 5.4 GB free | 6.2 GB 1× · 9.8 GB free |
| Mistral 7B Instruct v0.3 Mistral AI | 7.2B | 17 GB Tight on 1× · 10% spare | 9.6 GB 1× · 6.4 GB free | 5.6 GB 1× · 10 GB free |
| Qwen3 4B Alibaba | 4B | 9.7 GB 1× · 6.3 GB free | 5.3 GB 1× · 11 GB free | 3.1 GB 1× · 13 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
Want more from this page?
See incorrect data?
Frequently asked questions
How much VRAM does the V100 SXM2 have?
The V100 SXM2 comes with 16 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Which LLMs can I run on the V100 SXM2?
With 16 GB of VRAM, a single V100 SXM2 can serve models such as Gemma 3 12B, Granite 4.1 8B, Qwen3 8B, Llama 3.1 8B Instruct. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.