M2 Pro 32GB

APPLE · 32GB unified memory · 4 reports

On the M2 Pro 32GB, Qwen3.8 27B at 4-bit, the model most run on it, generates a median of 8.6 tokens per second from one plain run (community reports, as of 29 Oct 2026).

As of 29 Oct 2026, the models most run on the M2 Pro 32GB, with generation and prompt-processing medians from plain runs (one device, one request, no speculative decoding):

Qwen3.8 27B
8.6gen t/s at 4-bit · one run
PP 21.9 t/s · 1 run

Engines people use on it: llama.cpp 3 (reports) · MLX 1 (reports)

See reported performance Estimate what fits

How to compare these reports →Filter reports by setup →All M2 Macs compared →

Run models on your M2 Pro 32GB? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Benchmark with your agent Paste a result

Reported performance on the M2 Pro 32GB

These reports mix GPU counts and memory setups, so a model listed here may have needed extra cards or CPU offloading. The calculator estimates which models fit in 32 GB of unified memory.

Date ↓Date ↑Token speed ↓Token speed ↑Prefill ↓Prefill ↑Context ↓Context ↑Ranked

Code Llama 7B Instruct / Q4_K_M / M2 Pro 19-core / native phases

M2 Pro 32GB · llama.cpp

generation:: 33.6 tokens/s
prompt processing (prefill):: 200.7 tokens/s
quant:: Q4_K_M (GGUF)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.

User reports Code Llama 7B Instruct at 33.6 t/s generation and 200.7 t/s prompt processing on an M2 Pro 32GB Mac mini. Setup is llama.cpp with Metal, Q4_K_M GGUF, one Metal device, and a Japanese Fibonacci-code prompt at --temp 0.1. The figures are native eval phase timers from a single displayed run, not an end-to-end average; context length, layer count, and KV precision are unreported.

ALMA 7B-Ja / Q4_K_M / M2 Pro 19-core / native phases

M2 Pro 32GB · llama.cpp

generation:: 34.8 tokens/s
prompt processing (prefill):: 227.6 tokens/s
quant:: Q4_K_M (GGUF)

User reports ALMA-7B-Ja at 34.8 t/s generation and 227.6 t/s prompt processing on an M2 Pro 32GB. Setup is llama.cpp with Metal, Q4_K_M GGUF, run with -n 128; layer count, context length, batch size and KV precision are unreported. The figures are native request phase timers from one displayed run, not an end-to-end average, with no warmup or cache protocol.

Qwen3.6 35B (3B active)

M2 Pro 32GB · MLX

generation:: 61.7 tokens/s
prompt processing (prefill):: 276.8 tokens/s
quant:: 4-bit group-64 (MLX)

User reports Qwen3.6 35B-A3B at 61.7 t/s generation and 276.8 t/s prompt processing on a Mac mini with Apple M2 Pro and 32 GB unified memory. Setup is mlx-lm 0.31.3 with MLX 0.31.2, MLX 4-bit group-64 weights of about 19.0 GiB, temperature 0 and --max-tokens 128. The figures are medians of three runs on a 490-token prompt with 128 tokens generated; peak memory was 20.261 GB per run.

Qwen3.8 27B

M2 Pro 32GB · llama.cpp · 131,072 ctx

generation:: 8.6 tokens/s
prompt processing (prefill):: 21.9 tokens/s
quant:: IQ4_XS (GGUF)

codingvision

User reports Qwen3.8 27B IQ4_XS with vision projector on an M2 MacBook Pro 32GB, at 21.9 t/s prompt and 8.6 t/s generation. Setup is llama.cpp built from source, with context set to 128K due to memory constraints. User notes the model is slow on Mac but that thinking quality is good, and mentions previous experience with Qwen3.5 35B-A3B.

Get a weekly email of new M2 Pro 32GB reports and newly released models that fit it.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardware	Quant / engine	Reported context	Generation
Code Llama 7B Instruct / Q4_K_M / M2 Pro 19-core / native phases M2 Pro 32GB	Q4_K_M llama.cpp	Not reported	33.6 tokens/s
ALMA 7B-Ja / Q4_K_M / M2 Pro 19-core / native phases M2 Pro 32GB	Q4_K_M llama.cpp	Not reported	34.8 tokens/s
Qwen3.6 35B (3B active) M2 Pro 32GB	4-bit group-64 MLX	Not reported	61.7 tokens/s
Qwen3.8 27B M2 Pro 32GB	IQ4_XS llama.cpp	131,072	8.6 tokens/s

Frequently asked

How fast is the M2 Pro 32GB for local LLMs?

On the M2 Pro 32GB, Qwen3.8 27B at 4-bit, the model most run on it, generates a median of 8.6 tokens per second from one plain run (community reports, as of 29 Oct 2026).