Rent a GPU

Can the Apple M2 Ultra (192GB) run Llama 3.1 8B?

Apple M2 Ultra (192GB) × Llama 3.1 8B8K context
YesRuns fully on the GPU
Memory at FP1617.7 GB of 144 GB
Weights 16.1 GBKV cache 1.1 GBRuntime 0.6 GB
QuantFP16Full quality
Memory17.7 GBof 144 GB usable
Speed~30tokens 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 M2 Ultra (192GB) can run Llama 3.1 8B fully in unified memory at FP16 (full quality), using about 17.7 GB of the 144 GB available, at roughly 30 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 M2 Ultra (192GB)

Run it in the cloud

No Apple M2 Ultra (192GB)? 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 144 GB the Apple M2 Ultra (192GB) can use. macOS lets the GPU use about 144 GB of the 192 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality17.7 GBFits~30 tok/s
Q8_0Near-lossless10.2 GBFits~56 tok/s
Q6_KExcellent8.3 GBFits~73 tok/s
Q5_K_MVery good7.4 GBFits~84 tok/s
Q4_K_MGood, most popular6.5 GBFits~99 tok/s
Q3_K_MNoticeably degraded5.6 GBFits~122 tok/s
Q2_KHeavily degraded4.7 GBFits~159 tok/s

GPUs that run Llama 3.1 8B comfortably

Models that run well on the Apple M2 Ultra (192GB)

Frequently asked questions

Can Apple M2 Ultra (192GB) run Llama 3.1 8B?

Yes. The Apple M2 Ultra (192GB) can run Llama 3.1 8B fully in unified memory at FP16 (full quality), using about 17.7 GB of the 144 GB available, at roughly 30 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 M2 Ultra (192GB)?

Roughly 30 tokens per second at FP16, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.