⚠️Tight fitfp16 · 4K ctx · batch 1

Run Qwen3-8B on RTX 3090

At fp16 precision, Qwen3-8B (8.0 B parameters) needs roughly 20.2 GB of VRAM. RTX 3090 has 24 GB — fits, but only 3.8 GB spare. You'll want shorter sequences, batch 1, or INT8 quantization (6.3 GB at INT4).

84%
VRAM
Tight fit
Estimated VRAM (fp16)
20.2 GB
of 24 GB on RTX 3090· 3.8 GB free
Tok/sec
51
TFTT
1302ms
Power
134W
Rent on GPUniq marketplace
RTX 3090
Live prices from verified providers · billed hourly, no commitment.
Rent now

Memory breakdown (fp16)

Model Weights
16.00 GB
KV Cache
0.63 GB
Activations
2.50 GB
Framework Overhead
1.04 GB

Quantization comparison

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

PrecisionVRAMUtilisationFits on RTX 3090?
FP16 (full precision)20.2 GB84%⚠️Tight fit
INT8 (8-bit)10.9 GB45%✅Runs easily
INT4 / Q4 (4-bit)6.3 GB26%✅Runs easily

Frequently asked

Can RTX 3090 run Qwen3-8B?
Yes. Qwen3-8B needs ≈ 20.2 GB VRAM at fp16 and RTX 3090 provides 24 GB. Expected throughput is 51 tokens/sec per GPU.
How much VRAM does Qwen3-8B use?
About 20.2 GB at fp16, 6.3 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 3090?
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 3090, enable Flash Attention 2 and INT8/INT4 quantization to leave headroom for batching.
Where can I rent a RTX 3090?
GPUniq aggregates live RTX 3090 offers from verified providers. You can deploy an instance in about a minute and pay hourly with no commitment.

Other GPUs for Qwen3-8B

Other models on RTX 3090

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 →