Rent a GPU

Can the NVIDIA RTX 5090 run Qwen3 8B?

RTX 5090 × Qwen3 8B8K context
YesRuns fully on the GPU
Memory at FP1618.2 GB of 32 GB
Weights 16.4 GBKV cache 1.2 GBRuntime 0.6 GB
QuantFP16Full quality
Memory18.2 GBof 32 GB usable
Speed~66tokens 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 8B fully in VRAM at FP16 (full quality), using about 18.2 GB of the 32 GB available, at roughly 66 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3 8B:

ollama run qwen3:8b

Ollama's default download is Q4_K_M (about 6.8 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX 5090

Run it in the cloud

No NVIDIA RTX 5090? Run Qwen3 8B 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 quality18.2 GBFits~66 tok/s
Q8_0Near-lossless10.5 GBFits~124 tok/s
Q6_KExcellent8.5 GBFits~160 tok/s
Q5_K_MVery good7.6 GBFits~185 tok/s
Q4_K_MGood, most popular6.8 GBFits~217 tok/s
Q3_K_MNoticeably degraded5.8 GBFits~269 tok/s
Q2_KHeavily degraded4.9 GBFits~350 tok/s

GPUs that run Qwen3 8B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Qwen3 8B?

Yes. The NVIDIA RTX 5090 can run Qwen3 8B fully in VRAM at FP16 (full quality), using about 18.2 GB of the 32 GB available, at roughly 66 tokens/second.

How much VRAM does Qwen3 8B need?

About 6.8 GB at Q4_K_M with 8,192 tokens of context, and about 18.2 GB at full FP16 precision.

How fast is Qwen3 8B on the NVIDIA RTX 5090?

Roughly 66 tokens per second at FP16, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.