Rent a GPU

Can the Apple M3 Ultra (256GB) run MiniMax M3 428B-A23B?

Apple M3 Ultra (256GB) × MiniMax M3 428B-A23B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K161.7 GB of 192 GB
Weights 160.1 GBKV cache 1 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~57tokens per second
Max context247Ktokens 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. MiniMax M3 428B-A23B fits on the Apple M3 Ultra (256GB) at Q2_K, which costs noticeable quality. Expect about 57 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it in the cloud

Want full quality? Run MiniMax M3 428B-A23B 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 192 GB the Apple M3 Ultra (256GB) can use. macOS lets the GPU use about 192 GB of the 256 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality855.6 GBToo big—
Q8_0Near-lossless455.3 GBToo big—
Q6_KExcellent351.7 GBToo big—
Q5_K_MVery good305.3 GBToo big—
Q4_K_MGood, most popular260.5 GBToo big—
Q3_K_MNoticeably degraded210.3 GBToo big—
Q2_KHeavily degraded161.7 GBFits~57 tok/s

Measured speed from real Apple M3 Ultra (256GB) owners

Tokens per second that people measured on their own Apple M3 Ultra (256GB), next to our estimate.

No one has measured MiniMax M3 428B-A23B on the Apple M3 Ultra (256GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M3 Ultra (256GB)? Add your real speed

One command times MiniMax M3 428B-A23B 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 M3 Ultra (256GB)

Frequently asked questions

Can Apple M3 Ultra (256GB) run MiniMax M3 428B-A23B?

Only just. MiniMax M3 428B-A23B fits on the Apple M3 Ultra (256GB) at Q2_K, which costs noticeable quality. Expect about 57 tokens/second. A card with more memory is a better experience.

How much VRAM does MiniMax M3 428B-A23B need?

About 260.5 GB at Q4_K_M with 8,192 tokens of context, and about 855.6 GB at full FP16 precision.

How fast is MiniMax M3 428B-A23B on the Apple M3 Ultra (256GB)?

Roughly 57 tokens per second at Q2_K, estimated from the Apple M3 Ultra (256GB)'s 819 GB/s memory bandwidth.