Rent a GPU

Can the Apple M4 Max (128GB) run Llama 4 Scout 17B-16E?

Apple M4 Max (128GB) × Llama 4 Scout 17B-16E8K context
YesRuns fully on the GPU
Memory at Q6_K91.6 GB of 96 GB
Weights 89.4 GBKV cache 1.6 GBRuntime 0.6 GB
QuantQ6_KExcellent
Memory91.6 GBof 96 GB usable
Speed~24tokens per second
  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 M4 Max (128GB) can run Llama 4 Scout 17B-16E fully in unified memory at Q6_K (excellent), using about 91.6 GB of the 96 GB available, at roughly 24 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Llama 4 Scout 17B-16E:

ollama run llama4:scout

Ollama's default download is Q4_K_M (about 68.3 GB here). You have room for Q6_K, which is excellent: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No Apple M4 Max (128GB)? Run Llama 4 Scout 17B-16E 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 96 GB the Apple M4 Max (128GB) can use. macOS lets the GPU use about 96 GB of the 128 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality220.2 GBToo big—
Q8_0Near-lossless118 GBToo big—
Q6_KExcellent91.6 GBFits~24 tok/s
Q5_K_MVery good79.7 GBFits~27 tok/s
Q4_K_MGood, most popular68.3 GBFits~32 tok/s
Q3_K_MNoticeably degraded55.5 GBFits~39 tok/s
Q2_KHeavily degraded43.1 GBFits~51 tok/s

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

Models that run well on the Apple M4 Max (128GB)

Frequently asked questions

Can Apple M4 Max (128GB) run Llama 4 Scout 17B-16E?

Yes. The Apple M4 Max (128GB) can run Llama 4 Scout 17B-16E fully in unified memory at Q6_K (excellent), using about 91.6 GB of the 96 GB available, at roughly 24 tokens/second.

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 M4 Max (128GB)?

Roughly 24 tokens per second at Q6_K, estimated from the Apple M4 Max (128GB)'s 546 GB/s memory bandwidth.