Rent a GPU

DeepSeek R1 Distill Qwen 7B hardware requirements

7.62B parameters. Needs about 5.7 GB at Q4_K_M with 8K context.

Parameters7.62BDense
Q4_K_M · 8K5.7 GBthe usual download
FP16 · 8K16.3 GBfull precision
Runs well on51/51GPUs and Macs we track

Memory needed at each quantization

Weights, KV cache and runtime overhead, at 8K and 32K tokens of context.

QuantQuality8K context32K context
FP16Full quality16.3 GB17.7 GB
Q8_0Near-lossless9.2 GB10.6 GB
Q6_KExcellent7.3 GB8.7 GB
Q5_K_MVery good6.5 GB7.9 GB
Q4_K_MGood, most popular5.7 GB7.1 GB
Q3_K_MNoticeably degraded4.8 GB6.2 GB
Q2_KHeavily degraded3.9 GB5.3 GB

Run it with Ollama

Downloads Q4_K_M by default.

ollama run deepseek-r1:7b

Model card

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B on Hugging Face: licence, prompt format and GGUF builds.

Run it in the cloud

Run DeepSeek R1 Distill Qwen 7B on a rented GPU today.

It needs about 5.7 GB at Q4_K_M: a rented RTX 3090 / RTX 4090 runs it for about $0.18 to $0.89 an hour.

RunPodRent a GPU on RunPodVast.aiRent a GPU on Vast.ai

Every GPU and Mac checked

Sorted by memory. Bars show how much of each card DeepSeek R1 Distill Qwen 7B fills at the best quant that fits.

51 Runs well

NameMemory usedBest quantSpeed

Other DeepSeek models