V100 PCIe: 32 GB, what it runs and what it costs
Specs checked · Aliteq Team · How we compute this
The short answer
The NVIDIA Tesla V100 32GB PCIe has 32 GB of VRAM and 900 GB/s of memory bandwidth (2018). At Q4_K_M quality or better with an 8K context it runs 32 of the open models we track; the largest that fits with room to spare is Qwen3.6 35B-A3B (MoE). We don't see it for rent on the providers we track right now.
- VRAM
- 32 GB
- Bandwidth
- 900 GB/s
- Board power
- 250 W
- Launched
- 2018
Source: NVIDIA specification · bandwidth not yet confirmed by a second source, so we don't estimate speed from it
Buy it or rent it
Not for rent on the providers we track right now. See every card that is.
Which AI models run on the V100 PCIe
Computed by our VRAM engine for an 8K context: the best quality each model fits at in 32 GB. Speeds are upper-bound estimates from memory bandwidth, not benchmarks.
| Model | Best fit | VRAM used | ~tok/s |
|---|---|---|---|
| Mixtral 8x7B (MoE) | Q5_0 | 32 GB100% · tight | — |
| Qwen3.6 35B-A3B (MoE) | Q6_K | 28 GB89% | — |
| Ornith-1.5 35B-A3B (MoE) | Q6_K | 28 GB89% | — |
| Qwen3.5 35B-A3B (MoE) | Q6_K | 28 GB89% | — |
| DeepSeek R1 Distill 32B | Q6_K | 28 GB87% | — |
| Qwen2.5 Coder 32B | Q6_K | 28 GB87% | — |
| Qwen2.5 32B Instruct | Q6_K | 28 GB87% | — |
| Qwen3 32B | Q6_K | 28 GB87% | — |
| NVIDIA Nemotron 3 Nano 30B-A3B (MoE) | Q6_K | 25 GB78% | — |
| Gemma 4 31B | Q6_K | 25 GB79% | — |
| Qwen3 30B-A3B (MoE) | Q8_0 | 32 GB99% · tight | — |
| Qwen3-Coder 30B-A3B (MoE) | Q8_0 | 32 GB99% · tight | — |
Fits only below Q4 quality: Qwen3-Next 80B-A3B (MoE) (IQ3_XS), Qwen3-Coder-Next 80B-A3B (MoE) (IQ3_XS), DeepSeek R1 Distill 70B (Q2_K).
Too big for 32 GB (rent a bigger card instead): what it costs to run GLM-4.5-Air (MoE), what it costs to run Llama 4 Scout 17B-16E (MoE), what it costs to run gpt-oss 120B (MoE), what it costs to run NVIDIA Nemotron 3 Super 120B-A12B (MoE).
Check a model and context of your own in the VRAM calculator.
AI video on the V100 PCIe
Alibaba's Wan 2.2 is an open video model you can run yourself in ComfyUI. With 32 GB the V100 PCIe fits:
- Wan 2.2 14B at 640x640 with fp8 weights (24 GB and up, per Runpod's Wan 2.2 guide)
- Wan 2.2 5B, with ComfyUI's native offloading (8 GB and up, per ComfyUI's Wan 2.2 docs)
What each setup needs, the cheapest card to rent and what one clip costs: cloud GPUs for ComfyUI with Flux and Wan 2.2. Against an app or an API: AI video cost per clip, app vs API vs rented GPU. Rather not run a model yourself? Hosted video models such as Seedance, Veo and Hailuo are compared in Kling AI alternatives, priced per clip.
Our guides on the V100 PCIe
Cards to compare it with
Every card by VRAM tier: all GPUs for gaming and local AI.