Rent a GPU

Can the NVIDIA RTX 5090 run Qwen3 4B?

RTX 5090 × Qwen3 4B8K context
YesRuns fully on the GPU
Memory at FP169.8 GB of 32 GB
Weights 8 GBKV cache 1.2 GBRuntime 0.6 GB
QuantFP16Full quality
Memory9.8 GBof 32 GB usable
Speed~134tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 5090 can run Qwen3 4B fully in VRAM at FP16 (full quality), using about 9.8 GB of the 32 GB available, at roughly 134 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3 4B:

ollama run qwen3:4b

Ollama's default download is Q4_K_M (about 4.2 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 5090? Run Qwen3 4B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 32 GB the NVIDIA RTX 5090 can use.

QuantQualityMemoryFits?Speed
FP16Full quality9.8 GBFits~134 tok/s
Q8_0Near-lossless6.1 GBFits~252 tok/s
Q6_KExcellent5.1 GBFits~326 tok/s
Q5_K_MVery good4.7 GBFits~376 tok/s
Q4_K_MGood, most popular4.2 GBFits~441 tok/s
Q3_K_MNoticeably degraded3.8 GBFits~547 tok/s
Q2_KHeavily degraded3.3 GBFits~713 tok/s

GPUs that run Qwen3 4B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Qwen3 4B?

Yes. The NVIDIA RTX 5090 can run Qwen3 4B fully in VRAM at FP16 (full quality), using about 9.8 GB of the 32 GB available, at roughly 134 tokens/second.

How much VRAM does Qwen3 4B need?

About 4.2 GB at Q4_K_M with 8,192 tokens of context, and about 9.8 GB at full FP16 precision.

How fast is Qwen3 4B on the NVIDIA RTX 5090?

Roughly 134 tokens per second at FP16, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.