Apple

iMac 24-inch (M4, 2024)

Name: iMac 24-inch (M4, 2024)
Brand: Apple

M4Released November 8, 2024Launch price $1,499 (Apple US price since mid-2026 (launched at $1,299), 8-core GPU, 16GB / 256GB)

Best Buy · M4 8-core CPU, 8-core GPU, 16GB, 256GB, Silver Check price at Best Buy Amazon · M4 8-core CPU, 8-core GPU, 16GB, 256GB, Silver Check price on Amazon

Blender Benchmark 1,196samples/min#1 of 1

The all-in-one Mac: a 24-inch 4.5K display, camera, speakers and keyboard with an M4 inside, 8-core CPU and GPU in the two-port base model and 10-core in the four-port models. 16GB (up to 32GB) at 120GB/s runs 7-8B language models but is no AI workstation, and the chip is two years old - Bloomberg reports an M6 iMac is close, so wait unless you need one now.

Wait iMac 721days since update

Past the usual gap between updates: one is due. Last updated October 28, 2024, iMac 24-inch (M4); the last 4 updates came every 512 days on average. Next: An iMac with the M6 chip, expected to be announced around 27-28 October and released Friday, 6 November 2026. (MacRumors, citing Bloomberg's Mark Gurman, 2026-10-18)

Against the line-up

Blender Benchmark samples/min

#1 of 1 · Blender Open Data

1iMac M41,196

The whole iMac line-up side by side, with prices

Every benchmark

Quoted from the publications that ran them; we don't test hardware ourselves. Figures from different publications were run on different systems and scenes, so compare within a row's source.

Local LLM (llama.cpp / Ollama)

Setting	Result	Source
Llama 2 7B F16, Generation one source	7.43tok/s	llama.cpp community benchmarks (GitHub), Oct 19, 2026 M4, 10-core GPU, 120GB/s (four-port models) llama-bench tg128 (generating 128 tokens), all layers on the GPU.
Llama 2 7B Q4_0, Generation one source	24.1tok/s	llama.cpp community benchmarks (GitHub), Oct 19, 2026 M4, 10-core GPU, 120GB/s (four-port models) llama-bench tg128 (generating 128 tokens), all layers on the GPU. The 8-core GPU has no figure in the thread.
Llama 2 7B Q4_0, Prompt processing one source	221tok/s	llama.cpp community benchmarks (GitHub), Oct 19, 2026 M4, 10-core GPU, 120GB/s (four-port models) llama-bench pp512 (reading a 512-token prompt), all layers on the GPU.
Llama 2 7B Q8_0, Generation one source	13.5tok/s	llama.cpp community benchmarks (GitHub), Oct 19, 2026 M4, 10-core GPU, 120GB/s (four-port models) llama-bench tg128 (generating 128 tokens), all layers on the GPU.

Blender Benchmark

Setting	Result	Source
Standard run one source	1,196samples/min	Blender Open Data, Oct 19, 2026 Apple M4 (GPU - 8 cores), Metal, Blender 5.2.0 Median score over the three scenes, 9 submitted runs
10-core GPU one source	1,276samples/min	Blender Open Data, Oct 19, 2026 Apple M4 (GPU - 10 cores), Metal, Blender 5.2.0 Median score over the three scenes, 33 submitted runs
CPU one source	213samples/min	Blender Open Data, Oct 19, 2026 Apple M4 CPU, Blender 5.2.0 Median score over the three scenes, 41 submitted runs. All M4 Macs together.

Specs

Chip	Apple M4
CPU cores	8 (4 performance, 4 efficiency); 10 on four-port models
GPU cores	8; 10 on four-port models
Neural Engine	38 TOPS
Memory (base)	16 GB
Memory (max)	32 GB
Memory bandwidth	120 GB/s
Storage (base)	256 GB
Storage (max)	2 TB
Ports	2x Thunderbolt / USB 4 and headphone jack; four-port models: 4x Thunderbolt 4 and Gigabit Ethernet
External displays	1 external (2 on four-port models), plus the built-in 24-inch 4.5K

From Apple: iMac tech specs (2026-10-19), Apple Store: buy iMac (price) (2026-10-19), Apple Newsroom: the new iMac with M4 (2024-10-28), Apple Newsroom: Apple introduces M4 chip (Neural Engine) (2024-05-07).

Sources

Blender Open Data (results database)
llama.cpp community benchmarks (GitHub) (results database)

As an Amazon Associate we earn from qualifying purchases, and we may earn from other shop links. Amazon's price is on Amazon; Best Buy's is read from Best Buy and shown with the time it was checked.