Rent a GPU

Can the Apple M2 Ultra (192GB) run Qwen3.8 2.4T-A95B?

Apple M2 Ultra (192GB) × Qwen3.8 2.4T-A95B8K context
NoDoes not fit in memory
Memory at Q4_K_M1484.3 GB of 144 GB
Weights 1482.9 GBKV cache 0.8 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, Qwen3.8 2.4T-A95B needs about 1484.3 GB, but the Apple M2 Ultra (192GB) has 144 GB usable. You could offload some layers to system RAM, but it will be very slow.

Try other context lengths

Run it in the cloud

Too big for the Apple M2 Ultra (192GB)? Run Qwen3.8 2.4T-A95B 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 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 quality4893.4 GBToo big—
Q8_0Near-lossless2600.2 GBToo big—
Q6_KExcellent2007.1 GBToo big—
Q5_K_MVery good1741.1 GBToo big—
Q4_K_MGood, most popular1484.3 GBToo big—
Q3_K_MNoticeably degraded1196.9 GBToo big—
Q2_KHeavily degraded918.6 GBToo big—

Measured speed from real Apple M2 Ultra (192GB) owners

Tokens per second that people measured on their own Apple M2 Ultra (192GB), next to our estimate.

No one has measured Qwen3.8 2.4T-A95B on the Apple M2 Ultra (192GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M2 Ultra (192GB)? Add your real speed

One command times Qwen3.8 2.4T-A95B 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

Windows (PowerShell)

irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

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

Frequently asked questions

Can Apple M2 Ultra (192GB) run Qwen3.8 2.4T-A95B?

No. Even at Q4_K_M, Qwen3.8 2.4T-A95B needs about 1484.3 GB, but the Apple M2 Ultra (192GB) has 144 GB usable. You could offload some layers to system RAM, but it will be very slow.

How much VRAM does Qwen3.8 2.4T-A95B need?

About 1484.3 GB at Q4_K_M with 8,192 tokens of context, and about 4893.4 GB at full FP16 precision.

How fast is Qwen3.8 2.4T-A95B on the Apple M2 Ultra (192GB)?

It does not fit in the Apple M2 Ultra (192GB)'s memory, so most layers would run from system RAM and generation would be very slow.