Rent a GPU

Can the Apple M2 Pro (32GB) run Qwen3.8 27B?

Apple M2 Pro (32GB) × Qwen3.8 27B8K context
YesRuns fully on the GPU
Memory at Q5_K_M20.9 GB of 21.4 GB
Weights 19.8 GBKV cache 0.5 GBRuntime 0.6 GB
QuantQ5_K_MVery good
Speed~6tokens per second
Max context14Ktokens that fit at Q5_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

Yes. The Apple M2 Pro (32GB) can run Qwen3.8 27B fully in unified memory at Q5_K_M (very good), using about 20.9 GB of the 21.4 GB available, at roughly 6 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3.8 27B:

ollama run qwen3.8:27b

Ollama's default download is Q4_K_M (about 18 GB here). You have room for Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Apple M2 Pro (32GB)

Run it in the cloud

No Apple M2 Pro (32GB)? Run Qwen3.8 27B 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 21.4 GB the Apple M2 Pro (32GB) can use. macOS lets the GPU use about 21.4 GB of the 32 GB unified memory by default.

QuantQualityMemoryFits?Speed
FP16Full quality56.7 GBToo big—
Q8_0Near-lossless30.7 GBToo big—
Q6_KExcellent23.9 GBToo big—
Q5_K_MVery good20.9 GBFits~6 tok/s
Q4_K_MGood, most popular18 GBFits~7 tok/s
Q3_K_MNoticeably degraded14.7 GBFits~9 tok/s
Q2_KHeavily degraded11.6 GBFits~12 tok/s

Measured speed from real Apple M2 Pro (32GB) owners

Tokens per second that people measured on their own Apple M2 Pro (32GB), next to our estimate.

No one has measured Qwen3.8 27B on the Apple M2 Pro (32GB) yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an Apple M2 Pro (32GB)? Add your real speed

One command times Qwen3.8 27B 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 -- qwen3.8:27b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen3.8:27b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen3.8 27B comfortably

Models that run well on the Apple M2 Pro (32GB)

Frequently asked questions

Can Apple M2 Pro (32GB) run Qwen3.8 27B?

Yes. The Apple M2 Pro (32GB) can run Qwen3.8 27B fully in unified memory at Q5_K_M (very good), using about 20.9 GB of the 21.4 GB available, at roughly 6 tokens/second.

How much VRAM does Qwen3.8 27B need?

About 18 GB at Q4_K_M with 8,192 tokens of context, and about 56.7 GB at full FP16 precision.

How fast is Qwen3.8 27B on the Apple M2 Pro (32GB)?

Roughly 6 tokens per second at Q5_K_M, estimated from the Apple M2 Pro (32GB)'s 200 GB/s memory bandwidth.