Can TPU v5e run DeepSeek R1 Distill Qwen 7B?

Yes, the TPU v5e has 128GB VRAM and DeepSeek R1 Distill Qwen 7B requires approximately 3.9GB VRAM for Q4 quantization. Estimated inference speed: 964 tokens/second.

✅ — TPU v5e Can Run DeepSeek R1 Distill Qwen 7B

The TPU v5e packs 128GB VRAM. DeepSeek R1 Distill Qwen 7B needs ~3.9GB. You're good to go.

✅ Plenty of headroom

Hardware Specs

GPU: TPU v5e
VRAM: 128 GB
Bandwidth: 4500 GB/s
MSRP: $0

Model Requirements

Model: DeepSeek R1 Distill Qwen 7B
Parameters: 7B
VRAM (Q4): ~3.9 GB
Context: 128,000

Estimated Performance

964 tok/s

Estimated inference speed (Q4 quantization)

Run it locally with Ollama

ollama run deepseek-r1:7b

Requires Ollama installed on your machine

View on Ollama

DeepSeek R1 Distill Qwen 7B Details TPU v5e Specs

Try DeepSeek R1 Distill Qwen 7B on a different GPU

Try another model on TPU v5e

Full compatibility matrix

✅ — TPU v5e Can Run DeepSeek R1 Distill Qwen 7B

Hardware Specs

Model Requirements

Estimated Performance

Run it locally with Ollama

Try DeepSeek R1 Distill Qwen 7B on a different GPU

Try another model on TPU v5e

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab

✅ — TPU v5e Can Run DeepSeek R1 Distill Qwen 7B

Hardware Specs

Model Requirements

Estimated Performance

Run it locally with Ollama

Try DeepSeek R1 Distill Qwen 7B on a different GPU

Try another model on TPU v5e

Related Checks

More tools

VRAM Calculator

Cloud GPU Pricing

GPU Comparison

Compatibility Lab