Runs wellfp16 · 4K ctx · batch 1

Run Llama 3.1 8B on RTX 4090

At fp16 precision, Llama 3.1 8B (8.0 B parameters) needs roughly 17.7 GB of VRAM. RTX 4090 has 24 GB, leaving 6.3 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)
17.7 GB
of 24 GB on RTX 4090· 6.3 GB free
Tok/sec
49
TFTT
1178ms
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)17.7 GB74%Runs well
INT8 (8-bit)9.9 GB41%Runs easily
INT4 / Q4 (4-bit)6.0 GB25%Runs easily

Frequently asked

Can RTX 4090 run Llama 3.1 8B?
Yes. Llama 3.1 8B needs ≈ 17.7 GB VRAM at fp16 and RTX 4090 provides 24 GB. Expected throughput is 49 tokens/sec per GPU.
How much VRAM does Llama 3.1 8B use?
About 17.7 GB at fp16, 6.0 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 Llama 3.1 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 Llama 3.1 8B — no setup

Send a prompt and see how Llama 3.1 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 →