Rent a GPU

Qwen3 0.6B hardware requirements

0.75B parameters. Needs about 2 GB at Q4_K_M with 8K context.

Parameters0.75BDense
Q4_K_M · 8K2 GBthe usual download
FP16 · 8K3 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 quality3 GB5.9 GB
Q8_0Near-lossless2.3 GB5.2 GB
Q6_KExcellent2.2 GB5 GB
Q5_K_MVery good2.1 GB4.9 GB
Q4_K_MGood, most popular2 GB4.8 GB
Q3_K_MNoticeably degraded1.9 GB4.7 GB
Q2_KHeavily degraded1.8 GB4.6 GB

Run it with Ollama

Downloads Q4_K_M by default.

ollama run qwen3:0.6b

Model card

Qwen/Qwen3-0.6B on Hugging Face: licence, prompt format and GGUF builds.

Run it in the cloud

Run Qwen3 0.6B on a rented GPU today.

It needs about 2 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 Qwen3 0.6B fills at the best quant that fits.

51 Runs well

NameMemory usedBest quantSpeed

Other Qwen models