Runs wellfp16 · 4K ctx · batch 1

Run Qwen3-8B on RTX 4090

At fp16 precision, Qwen3-8B (8.0 B parameters) needs roughly 17.8 GB of VRAM. RTX 4090 has 24 GB, leaving 6.2 GB of headroom — plenty of room for longer contexts and larger batch sizes. Expected throughput ≈ 49 tokens/sec on a single card.

74%
VRAM
Runs well
Estimated VRAM (fp16)
17.8 GB
of 24 GB on RTX 4090· 6.2 GB free
Tok/sec
49
TFTT
1188ms
Power
267W
Rent on GPUniq marketplace
RTX 4090
Live prices from verified providers · billed hourly, no commitment.
Rent now

Memory breakdown (fp16)

Quantization comparison

Lower precision = less VRAM with a small quality trade-off. Quality order: FP16 > INT8 > INT4.

PrecisionVRAMUtilisationFits on RTX 4090?
FP16 (full precision)17.8 GB74%Runs well
INT8 (8-bit)11.0 GB46%Runs easily
INT4 / Q4 (4-bit)7.6 GB32%Runs easily

Frequently asked

Can RTX 4090 run Qwen3-8B?
Yes. Qwen3-8B needs ≈ 17.8 GB VRAM at fp16 and RTX 4090 provides 24 GB. Expected throughput is 49 tokens/sec per GPU.
How much VRAM does Qwen3-8B use?
About 17.8 GB at fp16, 7.6 GB at INT4 (for a 4K context, batch size 1). Longer contexts add to KV cache size; larger batches increase activations.
What's the fastest way to run Qwen3-8B on RTX 4090?
Use a production inference engine like vLLM, SGLang, or TensorRT-LLM with paged attention — they cut KV cache 2–3× vs the naive estimate and batch multiple requests efficiently. For RTX 4090, enable Flash Attention 2.
Where can I rent a RTX 4090?
GPUniq aggregates live RTX 4090 offers from verified providers. You can deploy an instance in about a minute and pay hourly with no commitment.
Try it live

Chat with Qwen3-8B — no setup

Send a prompt and see how Qwen3-8B responds directly in our chat. No installation, no GPU required to test.

Open in chat
Want to tweak sequence length, batch size, or fine-tuning? Open the full calculator →