Rent a GPU

Can the Apple M4 (16GB) run Llama 3.1 70B?

Apple M4 (16GB) × Llama 3.1 70B8K context
NoDoes not fit in memory
Memory at Q4_K_M46.1 GB of 10.7 GB
Weights 42.8 GBKV cache 2.7 GBRuntime 0.6 GB
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

No. Even at Q4_K_M, Llama 3.1 70B needs about 46.1 GB, but the Apple M4 (16GB) has 10.7 GB usable. You could offload some layers to system RAM, but it will be very slow.

Try other context lengths

Run it on a rented GPU

On a cloud GPU with enough memory, the same command you'd use locally works:

ollama run llama3.1:70b

At Q4_K_M it needs about 46.1 GB, so pick a GPU with at least 48 GB.

New to this? Step-by-step setup for the Apple M4 (16GB)

Run it in the cloud

Too big for the Apple M4 (16GB)? Run Llama 3.1 70B on a rented GPU instead.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

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 M4 (16GB) can use. macOS lets the GPU use about 10.7 GB of the 16 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality144.5 GBToo big—
Q8_0Near-lossless78.3 GBToo big—
Q6_KExcellent61.2 GBToo big—
Q5_K_MVery good53.5 GBToo big—
Q4_K_MGood, most popular46.1 GBToo big—
Q3_K_MNoticeably degraded37.8 GBToo big—
Q2_KHeavily degraded29.8 GBToo big—

Measured speed from real Apple M4 (16GB) owners

Tokens per second that people measured on their own Apple M4 (16GB), next to our estimate.

No one has measured Llama 3.1 70B on the Apple M4 (16GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M4 (16GB)? Add your real speed

One command times Llama 3.1 70B 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 -- llama3.1:70b

Windows (PowerShell)

$env:GPUFIT_MODEL="llama3.1:70b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Llama 3.1 70B comfortably

Models that run well on the Apple M4 (16GB)

Frequently asked questions

Can Apple M4 (16GB) run Llama 3.1 70B?

No. Even at Q4_K_M, Llama 3.1 70B needs about 46.1 GB, but the Apple M4 (16GB) has 10.7 GB usable. You could offload some layers to system RAM, but it will be very slow.

How much VRAM does Llama 3.1 70B need?

About 46.1 GB at Q4_K_M with 8,192 tokens of context, and about 144.5 GB at full FP16 precision.

How fast is Llama 3.1 70B on the Apple M4 (16GB)?

It does not fit in the Apple M4 (16GB)'s memory, so most layers would run from system RAM and generation would be very slow.