Rent a GPU

Can the Apple M2 Ultra (192GB) run DeepSeek V4 Flash 284B-A13B?

Apple M2 Ultra (192GB) × DeepSeek V4 Flash 284B-A13B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M139.6 GB of 144 GB
Weights 138.8 GBKV cache 0.2 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Speed~76tokens per second
Max context176Ktokens that fit at Q3_K_M
  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. DeepSeek V4 Flash 284B-A13B fits on the Apple M2 Ultra (192GB) at Q3_K_M, which costs noticeable quality. Expect about 76 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default deepseek-v4-flash download is Q4_K_M, which needs about 173 GB, more than the 144 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the Apple M2 Ultra (192GB)

Run it in the cloud

Want full quality? Run DeepSeek V4 Flash 284B-A13B 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 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 quality568.8 GBToo big—
Q8_0Near-lossless302.6 GBToo big—
Q6_KExcellent233.7 GBToo big—
Q5_K_MVery good202.8 GBToo big—
Q4_K_MGood, most popular173 GBToo big—
Q3_K_MNoticeably degraded139.6 GBFits~76 tok/s
Q2_KHeavily degraded107.3 GBFits~98 tok/s

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 DeepSeek V4 Flash 284B-A13B 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 DeepSeek V4 Flash 284B-A13B 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 -s -- deepseek-v4-flash

Windows (PowerShell)

$env:GPUFIT_MODEL="deepseek-v4-flash"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run DeepSeek V4 Flash 284B-A13B comfortably

Check Mac Studio M3 Ultra (256 GB) prices

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

Frequently asked questions

Can Apple M2 Ultra (192GB) run DeepSeek V4 Flash 284B-A13B?

Only just. DeepSeek V4 Flash 284B-A13B fits on the Apple M2 Ultra (192GB) at Q3_K_M, which costs noticeable quality. Expect about 76 tokens/second. A card with more memory is a better experience.

How much VRAM does DeepSeek V4 Flash 284B-A13B need?

About 173 GB at Q4_K_M with 8,192 tokens of context, and about 568.8 GB at full FP16 precision.

How fast is DeepSeek V4 Flash 284B-A13B on the Apple M2 Ultra (192GB)?

Roughly 76 tokens per second at Q3_K_M, estimated from the Apple M2 Ultra (192GB)'s 800 GB/s memory bandwidth.