Rent a GPU

Can the Apple M1 Max (64GB) run Llama 3.1 8B?

Apple M1 Max (64GB) × Llama 3.1 8B8K context
YesRuns fully on the GPU
Memory at FP1617.7 GB of 48 GB
Weights 16.1 GBKV cache 1.1 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~15tokens per second
Max context128Kthe model's full window
  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 M1 Max (64GB) can run Llama 3.1 8B fully in unified memory at FP16 (full quality), using about 17.7 GB of the 48 GB available, at roughly 15 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 FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M1 Max (64GB)

Run it in the cloud

No Apple M1 Max (64GB)? 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 48 GB the Apple M1 Max (64GB) can use. macOS lets the GPU use about 48 GB of the 64 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality17.7 GBFits~15 tok/s
Q8_0Near-lossless10.2 GBFits~28 tok/s
Q6_KExcellent8.3 GBFits~36 tok/s
Q5_K_MVery good7.4 GBFits~42 tok/s
Q4_K_MGood, most popular6.5 GBFits~49 tok/s
Q3_K_MNoticeably degraded5.6 GBFits~61 tok/s
Q2_KHeavily degraded4.7 GBFits~80 tok/s

Measured speed from real Apple M1 Max (64GB) owners

Tokens per second that people measured on their own Apple M1 Max (64GB), next to our estimate.

No one has measured Llama 3.1 8B on the Apple M1 Max (64GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M1 Max (64GB)? 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 M1 Max (64GB)

Frequently asked questions

Can Apple M1 Max (64GB) run Llama 3.1 8B?

Yes. The Apple M1 Max (64GB) can run Llama 3.1 8B fully in unified memory at FP16 (full quality), using about 17.7 GB of the 48 GB available, at roughly 15 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 M1 Max (64GB)?

Roughly 15 tokens per second at FP16, estimated from the Apple M1 Max (64GB)'s 400 GB/s memory bandwidth.