Rent a GPU

Can the Apple M1 Max (64GB) run Llama 4 Scout 17B-16E?

Apple M1 Max (64GB) × Llama 4 Scout 17B-16E8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K43.1 GB of 48 GB
Weights 40.9 GBKV cache 1.6 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~38tokens per second
Max context31Ktokens that fit at Q2_K
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Only just. Llama 4 Scout 17B-16E fits on the Apple M1 Max (64GB) at Q2_K, which costs noticeable quality. Expect about 38 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default llama4:scout download is Q4_K_M, which needs about 68.3 GB, more than the 48 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.

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

Run it in the cloud

Want full quality? Run Llama 4 Scout 17B-16E on a bigger rented GPU.

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 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 quality220.2 GBToo big—
Q8_0Near-lossless118 GBToo big—
Q6_KExcellent91.6 GBToo big—
Q5_K_MVery good79.7 GBToo big—
Q4_K_MGood, most popular68.3 GBToo big—
Q3_K_MNoticeably degraded55.5 GBToo big—
Q2_KHeavily degraded43.1 GBFits~38 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 4 Scout 17B-16E 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 4 Scout 17B-16E 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 -- llama4:scout

Windows (PowerShell)

$env:GPUFIT_MODEL="llama4:scout"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Llama 4 Scout 17B-16E comfortably

Check RTX PRO 6000 Blackwell prices

Models that run well on the Apple M1 Max (64GB)

Frequently asked questions

Can Apple M1 Max (64GB) run Llama 4 Scout 17B-16E?

Only just. Llama 4 Scout 17B-16E fits on the Apple M1 Max (64GB) at Q2_K, which costs noticeable quality. Expect about 38 tokens/second. A card with more memory is a better experience.

How much VRAM does Llama 4 Scout 17B-16E need?

About 68.3 GB at Q4_K_M with 8,192 tokens of context, and about 220.2 GB at full FP16 precision.

How fast is Llama 4 Scout 17B-16E on the Apple M1 Max (64GB)?

Roughly 38 tokens per second at Q2_K, estimated from the Apple M1 Max (64GB)'s 400 GB/s memory bandwidth.