Tesla V100 32GB Price & Used Prices: Which Local LLMs Can It Run?
The Tesla V100 32GB has 32GB of HBM2 memory with 900 GB/s of bandwidth. The median asking price is about $476 on Xianyu. At Q4 quantization it runs models up to 32B parameters at roughly 32 tokens/s.
Tesla V100 32GB price history
Xianyu
Full Tesla V100 32GB specifications
What LLMs can the Tesla V100 32GB run?
Versions released since 2026 with up to 50B parameters| Model | 2-bit | 4-bit | 8-bit | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Fits | Speed t/s | Context | Fits | Speed t/s | Context | Fits | Speed t/s | Context | |
| GemmaGemma 4 E4B | ✓ | 162.7 | 128K | ✓ | 116.8 | 128K | ✓ | 67.7 | 128K |
| QwenQwen3.5 9B | ✓ | 134.9 | 128K | ✓ | 96.9 | 128K | ✓ | 56.1 | 128K |
| GemmaGemma 4 12B | ✓ | 96.2 | 32K | ✓ | 71.4 | 32K | ✓ | 42.9 | 32K |
| GemmaGemma 4 26B A4B | ✓ | 126.6 | 32K | ✓ | 109.8 | 32K | ✓ | 81.8 | 8K |
| QwenQwen3.6 27B | ✓ | 52.2 | 32K | ✓ | 36.3 | 32K | ✓ | 20.4 | 8K |
| QwenQwen3.8 27B | ✓ | 52.2 | 32K | ✓ | 36.3 | 32K | ✓ | 20.4 | 8K |
| GLMGLM 4.7 Flash | ✓ | 162.9 | 128K | ✓ | 142 | 128K | Offload | 22.1 | — |
| GemmaGemma 4 31B | ✓ | 39 | 8K | ✓ | 28.5 | 8K | ✗ | — | — |
| QwenQwen3.6 35B A3B | ✓ | 158.6 | 128K | ✓ | 138.7 | 128K | Offload | 32.5 | — |
Fits when weights + KV cache + runtime overhead is at or below usable memory, single card. "Offload" on MoE models means it runs with expert weights in system RAM (only attention layers and KV cache stay in VRAM); that speed assumes 70 GB/s RAM bandwidth. The context column is the largest tier that fits.
Prices by platform
Buy links may carry affiliate tags; they do not change the price you pay.
FAQ
How much VRAM does the Tesla V100 32GB have?
The Tesla V100 32GB has 32GB of HBM2 memory with 900 GB/s of bandwidth.
Can the Tesla V100 32GB run a 70B model?
Not on a single card. At Q4_K_M with an 8K context a 70B dense model needs about 43GB, more than the Tesla V100 32GB's 32GB.
How much does a Tesla V100 32GB cost?
The median asking price is about $476 on Xianyu. Figures are medians of live listings, refreshed every 6 hours.