Best local LLM for summarization on a Apple M2 Max (64GB) (2026)
All figures assume an f16 KV cache, a 0.6 GB display reserve on the GPU, and 64 GB of DDR5 system RAM for the offload tiers. Tune these in the calculator.
The verdict
Qwen3.5 27B Q8_0
Fits on GPU at 32K · Summarization score 8/10 · ≈ 9 tok/s
The dense 24GB workhorse. If you want one model on a 3090 and no surprises, it's this.
llama-server -m Qwen3.5-27B-Q8_0.gguf -c 32768 --flash-attn -ngl 99
Worthy alternates
Qwen3.5 35B A3B Q8_0
Fits on GPU · ≈ 44 tok/s · Summarization 8/10
The meta pick, full stop. Near-dense-30B quality at 3B-active speed, and expert offload puts it on 8 GB cards.
Gemma 3 27B Q8_0
Fits on GPU · ≈ 9 tok/s · Summarization 8/10
Sliding-window attention keeps long context cheap, and the vision stack still beats most of 2026's newcomers.
Tune this for your exact RAM and settings in the calculator → · All models on the Apple M2 Max (64GB)
Frequently asked questions
What is the best local LLM for summarization on a Apple M2 Max (64GB)?
Qwen3.5 27B at Q8_0 — it scores 8/10 for summarization and runs as "Fits on GPU" at 32K context on the Apple M2 Max (64GB).
How much context do I need for summarization?
We recommend 48K tokens for summarization (minimum 24K). These picks are computed at 32K.
How fast will it run on a Apple M2 Max (64GB)?
Roughly 9 tokens/sec for Qwen3.5 27B — usable for interactive use.
Do I need more than 48 GB of VRAM for summarization?
No — the pick above needs 36.6 GB of VRAM at 32K.
What settings should I use?
Start with our command: llama-server -m Qwen3.5-27B-Q8_0.gguf -c 32768 --flash-attn -ngl 99 — then tune context and KV quant in the fit calculator.