Rent a GPU

Can the NVIDIA RTX 5080 run Llama 3.1 8B?

RTX 5080 × Llama 3.1 8B8K context
YesRuns fully on the GPU
Memory at Q8_010.2 GB of 16 GB
Weights 8.5 GBKV cache 1.1 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Memory10.2 GBof 16 GB usable
Speed~68tokens 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 5080 can run Llama 3.1 8B fully in VRAM at Q8_0 (near-lossless), using about 10.2 GB of the 16 GB available, at roughly 68 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Llama 3.1 8B:

ollama run llama3.1:8b

Ollama's default download is Q4_K_M (about 6.5 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 5080? Run Llama 3.1 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 16 GB the NVIDIA RTX 5080 can use.

QuantQualityMemoryFits?Speed
FP16Full quality17.7 GBToo big—
Q8_0Near-lossless10.2 GBFits~68 tok/s
Q6_KExcellent8.3 GBFits~87 tok/s
Q5_K_MVery good7.4 GBFits~101 tok/s
Q4_K_MGood, most popular6.5 GBFits~118 tok/s
Q3_K_MNoticeably degraded5.6 GBFits~147 tok/s
Q2_KHeavily degraded4.7 GBFits~191 tok/s

GPUs that run Llama 3.1 8B comfortably

Models that run well on the NVIDIA RTX 5080

Frequently asked questions

Can NVIDIA RTX 5080 run Llama 3.1 8B?

Yes. The NVIDIA RTX 5080 can run Llama 3.1 8B fully in VRAM at Q8_0 (near-lossless), using about 10.2 GB of the 16 GB available, at roughly 68 tokens/second.

How much VRAM does Llama 3.1 8B need?

About 6.5 GB at Q4_K_M with 8,192 tokens of context, and about 17.7 GB at full FP16 precision.

How fast is Llama 3.1 8B on the NVIDIA RTX 5080?

Roughly 68 tokens per second at Q8_0, estimated from the NVIDIA RTX 5080's 960 GB/s memory bandwidth.