Rent a GPU

Can the NVIDIA RTX 5090 run Qwen3 1.7B?

RTX 5090 × Qwen3 1.7B8K context
YesRuns fully on the GPU
Memory at FP165.6 GB of 32 GB
Weights 4.1 GBKV cache 0.9 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~265tokens per second
Max context32Kthe model's full window
  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 1.7B fully in VRAM at FP16 (full quality), using about 5.6 GB of the 32 GB available, at roughly 265 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3 1.7B:

ollama run qwen3:1.7b

Ollama's default download is Q4_K_M (about 2.8 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 1.7B 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 quality5.6 GBFits~265 tok/s
Q8_0Near-lossless3.7 GBFits~498 tok/s
Q6_KExcellent3.2 GBFits~646 tok/s
Q5_K_MVery good3 GBFits~745 tok/s
Q4_K_MGood, most popular2.8 GBFits~874 tok/s
Q3_K_MNoticeably degraded2.5 GBFits~1084 tok/s
Q2_KHeavily degraded2.3 GBFits~1412 tok/s

Measured speed from real RTX 5090 owners

Tokens per second that people measured on their own NVIDIA RTX 5090, next to our estimate.

No one has measured Qwen3 1.7B on the NVIDIA RTX 5090 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 5090? Add your real speed

One command times Qwen3 1.7B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- qwen3:1.7b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen3:1.7b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen3 1.7B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Qwen3 1.7B?

Yes. The NVIDIA RTX 5090 can run Qwen3 1.7B fully in VRAM at FP16 (full quality), using about 5.6 GB of the 32 GB available, at roughly 265 tokens/second.

How much VRAM does Qwen3 1.7B need?

About 2.8 GB at Q4_K_M with 8,192 tokens of context, and about 5.6 GB at full FP16 precision.

How fast is Qwen3 1.7B on the NVIDIA RTX 5090?

Roughly 265 tokens per second at FP16, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.