M2 Max 32GB

APPLE · 32GB unified memory · 3 reports

On the M2 Max 32GB, Qwen3.6 35B · 3B active at 4-bit, the model most run on it, generates a median of 39.3 tokens per second from 2 plain runs (community reports, as of 29 Oct 2026).

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

Qwen3.6 35B · 3B active
39.3gen t/s at 4-bit · 2 runs
PP 671.4 t/s · 1 run
Ornith1.5 35B · 3B active
108.0gen t/s at 4-bit · one run

Engines people use on it: llama.cpp 1 (reports) · oMLX 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 Max 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 Max 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

Ornith1.5 35B (3B active)

M2 Max 32GB · oMLX

generation:: 108.0 tokens/s
quant:: 4-bit (MLX)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.

User reports Ornith 1.5 35B-A3B at 108 tok/s on an M2 Max 32GB, versus 66 tok/s with the macOS Aerial lock-screen animation playing. Setup is oMLX with a 4-bit MoE model, medians of 4-6 local runs over 512 output tokens. After an 8k-token prompt, generation was 89 vs 66 tok/s, and WindowServer CPU use rose from roughly 25% to 44% while the animation ran. Using caffeinate -i instead of -d let the display sleep and restored speed.

Qwen3.6 35B (3B active)

M2 Max 32GB · llama.cpp · 4,096 ctx

generation:: 58.6 tokens/s
prompt processing (prefill):: 671.4 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 benchmarks Qwen3.6-35B-A3B at 58.56 t/s generation and 671.40 t/s prefill on an M2 Max 32GB. Setup is llama.cpp build c1d0e7a00 with Metal backend, Q4_K_M GGUF (20.22 GiB), 4096-token prompt, no speculative decoding. The dataset reports mostly negative results: MoE beats dense Qwen3.8-27B by 5.4x generation, aggressive quantization bought little, MTP and DFlash2 speculative decoding were net losses on Metal, and q8_0 KV cache was free. MLX reached 86.9 t/s generation but only 296 t/s prefill versus llama.cpp's 57.8 t/s and 685 t/s. oMLX with paged SSD KV cache reached 13.7 t/s generation and 84 t/s prefill on the dense 27B.

Qwen3.6 35B (3B active)

M2 Max 32GB · 60,000 ctx

generation:: 20.0 tokens/s
quant:: Q4_XS (GGUF)
kv:: Q8

agentic

User reports Qwen3.6 35B A3B at 15-20 t/s on an M2 Max 32GB, with prompt processing taking 20 minutes for 40k tokens when the model fits in RAM. Setup is Q4_XS GGUF at 60,000 context with a Q8 KV cache. With SSD streaming the model runs at 4-10 t/s and prompt processing takes 50-60 minutes for 40-60k tokens. User asks whether to upgrade to an M1 Max 64GB, M3 Max 128GB, or a 24GB GPU build with 128GB RAM.

Get a weekly email of new M2 Max 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
Ornith1.5 35B (3B active) M2 Max 32GB	4-bit oMLX	Not reported	108.0 tokens/s
Qwen3.6 35B (3B active) M2 Max 32GB	Q4_K_M llama.cpp	4,096	58.6 tokens/s
Qwen3.6 35B (3B active) M2 Max 32GB	Q4_XS Engine not reported	60,000	20.0 tokens/s

Frequently asked

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

On the M2 Max 32GB, Qwen3.6 35B · 3B active at 4-bit, the model most run on it, generates a median of 39.3 tokens per second from 2 plain runs (community reports, as of 29 Oct 2026). Also reported: Ornith1.5 35B · 3B active at 4-bit (108.0 t/s, one plain run).