# NVIDIA Tesla V100 32GB for local LLMs

> 900 GB/s HBM2 and tensor cores for mid-range money, with adapter and cooling caveats.

The V100 32GB has 32GB of HBM2 and 900 GB/s of memory bandwidth, which decides how big a model fits and how fast it generates text. It comfortably runs models up to about 35B parameters: the largest in our catalog is Qwen3.6 35B-A3B at Q5_K_M (28GB with 8K context, ~105 tokens/sec). Our top all-round pick for it is Qwen3.8 27B (Q6_K, ~25 tokens/sec).

## Key specs

- Memory: 32GB HBM2
- Memory bandwidth: 900 GB/s
- Architecture: Volta (2018)
- Power: 300W
- Typical price: ~$700 used (checked 2026-10)
- Software: CUDA, Vulkan

## Best models for this GPU

- **Best overall (also coding, reasoning, vision):** Qwen3.8 27B at Q6_K, ~24.8GB with 8K context, ~25 tokens/sec
- **Runner-up (also fastest, largest that fits):** Qwen3.6 35B-A3B at Q5_K_M, ~27.7GB with 8K context, ~105 tokens/sec

## Compatibility (best quantization that fits, 8K context)

| Model | Params | Quant | Memory | Speed | Verdict |
| --- | --- | --- | --- | --- | --- |
| Gemma 4 E4B | 8B | Q8_0 | 10.5GB | ~58 tok/s | Runs well |
| Qwen3.5 9B | 9B | Q8_0 | 12.0GB | ~51 tok/s | Runs well |
| Phi-4 | 14.7B | Q8_0 | 18.3GB | ~36 tok/s | Runs well |
| gpt-oss-20b | 20.9B (3.6B active) | MXFP4 | 15.0GB | ~100 tok/s | Runs well |
| Gemma 4 26B A4B | 26B (3.8B active) | Q6_K | 23.2GB | ~84 tok/s | Runs well |
| Qwen3.8 27B | 27B | Q6_K | 24.8GB | ~25 tok/s | Runs well |
| Gemma 4 31B | 31B | Q5_K_M | 26.0GB | ~25 tok/s | Runs well |
| Qwen3.6 35B-A3B | 35B (3B active) | Q5_K_M | 27.7GB | ~105 tok/s | Runs well |
| GLM-4.5-Air | 106B (12B active) | Q4_K_M | 68.3GB | ~9.6 tok/s | Partial offload |
| Llama 4 Scout | 109B (17B active) | Q4_K_M | 69.5GB | ~6.8 tok/s | Partial offload |
| gpt-oss-120b | 117B (5.1B active) | MXFP4 | 68.3GB | ~24 tok/s | Partial offload |
| Qwen3.5 122B-A10B | 122B (10B active) | Q4_K_M | 77.0GB | ~11 tok/s | Partial offload |
| DeepSeek V4 Flash | 284B (13B active) | - | - | - | Won't fit |
| GLM-5.3-Flash | 320B (18B active) | - | - | - | Won't fit |
| GLM-5.3 | 744B (40B active) | - | - | - | Won't fit |

## Pros
- 900 GB/s HBM2 bandwidth
- 32GB per card
- Tensor cores give faster prompt processing than Pascal

## Cons
- SXM2 modules need adapters and custom cooling
- Not supported by CUDA 13
- No display outputs

Full page: https://llamabuilds.ai/gpus/tesla-v100-32gb · Best models: https://llamabuilds.ai/gpus/tesla-v100-32gb/best-models

Sources: [NVIDIA Tesla V100 product page](https://www.nvidia.com/en-gb/data-center/tesla-v100/)

---
Source: https://llamabuilds.ai/gpus/tesla-v100-32gb · Updated October 14, 2026 · Llama Builds. Speeds marked ~ are estimates from our bandwidth model (https://llamabuilds.ai/methodology); measured results are labeled as such.