Rent a GPU

Can the Apple M5 (16GB) run Llama 3.1 8B?

Apple M5 (16GB) × Llama 3.1 8B8K context
YesRuns fully on the GPU
Memory at Q8_010.2 GB of 10.7 GB
Weights 8.5 GBKV cache 1.1 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~11tokens per second
Max context10Ktokens that fit at Q8_0
  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 Apple M5 (16GB) can run Llama 3.1 8B fully in unified memory at Q8_0 (near-lossless), using about 10.2 GB of the 10.7 GB available, at roughly 11 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.

New to this? Step-by-step setup for the Apple M5 (16GB)

Run it in the cloud

No Apple M5 (16GB)? 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 10.7 GB the Apple M5 (16GB) can use. macOS lets the GPU use about 10.7 GB of the 16 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality17.7 GBToo big—
Q8_0Near-lossless10.2 GBFits~11 tok/s
Q6_KExcellent8.3 GBFits~14 tok/s
Q5_K_MVery good7.4 GBFits~16 tok/s
Q4_K_MGood, most popular6.5 GBFits~19 tok/s
Q3_K_MNoticeably degraded5.6 GBFits~23 tok/s
Q2_KHeavily degraded4.7 GBFits~30 tok/s

Measured speed from real Apple M5 (16GB) owners

Tokens per second that people measured on their own Apple M5 (16GB), next to our estimate.

No one has measured Llama 3.1 8B on the Apple M5 (16GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M5 (16GB)? 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 Apple M5 (16GB)

Frequently asked questions

Can Apple M5 (16GB) run Llama 3.1 8B?

Yes. The Apple M5 (16GB) can run Llama 3.1 8B fully in unified memory at Q8_0 (near-lossless), using about 10.2 GB of the 10.7 GB available, at roughly 11 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 Apple M5 (16GB)?

Roughly 11 tokens per second at Q8_0, estimated from the Apple M5 (16GB)'s 153 GB/s memory bandwidth.