Rent a GPU

Can the NVIDIA RTX 5060 run Llama 3.1 8B?

RTX 5060 × Llama 3.1 8B8K context
YesRuns fully on the GPU
Memory at Q5_K_M7.4 GB of 8 GB
Weights 5.7 GBKV cache 1.1 GBRuntime 0.6 GB
QuantQ5_K_MVery good
Speed~47tokens per second
Max context11Ktokens that fit at Q5_K_M
  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 5060 can run Llama 3.1 8B fully in VRAM at Q5_K_M (very good), using about 7.4 GB of the 8 GB available, at roughly 47 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 Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX 5060

Run it in the cloud

No NVIDIA RTX 5060? 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 8 GB the NVIDIA RTX 5060 can use.

QuantQualityMemoryFits?Speed
FP16Full quality17.7 GBToo big—
Q8_0Near-lossless10.2 GBToo big—
Q6_KExcellent8.3 GBToo big—
Q5_K_MVery good7.4 GBFits~47 tok/s
Q4_K_MGood, most popular6.5 GBFits~55 tok/s
Q3_K_MNoticeably degraded5.6 GBFits~68 tok/s
Q2_KHeavily degraded4.7 GBFits~89 tok/s

Measured speed from real RTX 5060 owners

Tokens per second that people measured on their own NVIDIA RTX 5060, next to our estimate.

No one has measured Llama 3.1 8B on the NVIDIA RTX 5060 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 5060? Add your real speed

One command times Llama 3.1 8B 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 -- llama3.1:8b

Windows (PowerShell)

$env:GPUFIT_MODEL="llama3.1:8b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Llama 3.1 8B comfortably

Models that run well on the NVIDIA RTX 5060

Frequently asked questions

Can NVIDIA RTX 5060 run Llama 3.1 8B?

Yes. The NVIDIA RTX 5060 can run Llama 3.1 8B fully in VRAM at Q5_K_M (very good), using about 7.4 GB of the 8 GB available, at roughly 47 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 5060?

Roughly 47 tokens per second at Q5_K_M, estimated from the NVIDIA RTX 5060's 448 GB/s memory bandwidth.