Can the Apple M3 Ultra (256GB) run Kimi K3.1 Pro 2.8T-A104B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
No. Even at Q4_K_M, Kimi K3.1 Pro 2.8T-A104B needs about 1698.3 GB, but the Apple M3 Ultra (256GB) has 192 GB usable. You could offload some layers to system RAM, but it will be very slow.
Run it in the cloud
Too big for the Apple M3 Ultra (256GB)? Run Kimi K3.1 Pro 2.8T-A104B 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.
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.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 5600.8 GB | Too big | — | |
| Q8_0 | Near-lossless | 2975.8 GB | Too big | — | |
| Q6_K | Excellent | 2296.8 GB | Too big | — | |
| Q5_K_M | Very good | 1992.3 GB | Too big | — | |
| Q4_K_M | Good, most popular | 1698.3 GB | Too big | — | |
| Q3_K_M | Noticeably degraded | 1369.3 GB | Too big | — | |
| Q2_K | Heavily degraded | 1050.8 GB | Too big | — |
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 Kimi K3.1 Pro 2.8T-A104B 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 Kimi K3.1 Pro 2.8T-A104B 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 | shWindows (PowerShell)
irm https://gpufit.dev/bench.ps1 | iexFrequently asked questions
Can Apple M3 Ultra (256GB) run Kimi K3.1 Pro 2.8T-A104B?
No. Even at Q4_K_M, Kimi K3.1 Pro 2.8T-A104B needs about 1698.3 GB, but the Apple M3 Ultra (256GB) has 192 GB usable. You could offload some layers to system RAM, but it will be very slow.
How much VRAM does Kimi K3.1 Pro 2.8T-A104B need?
About 1698.3 GB at Q4_K_M with 8,192 tokens of context, and about 5600.8 GB at full FP16 precision.
How fast is Kimi K3.1 Pro 2.8T-A104B on the Apple M3 Ultra (256GB)?
It does not fit in the Apple M3 Ultra (256GB)'s memory, so most layers would run from system RAM and generation would be very slow.