llmrun
AppleM3Desktop

Best AI Models for iMac 24" M3 (24 GB)

Memory:24 GB UnifiedBandwidth:102.4 GB/sGPU Cores:10 GPU coresCPU Cores:8 CPU coresNeural Engine:18.0 TOPS

24 GB unified − 3.5 GB OS overhead = 20.5 GB available for AI models

How does this device compare with your machine?

37 of 293 featured models run great on iMac 24" M3 (24 GB) · best pick: Qwen3.8 27B at ~4.1 tok/s

largest that fits: 36.0B (Qwen3.6 35B A3B, IQ4_XS) · 70B needs CPU offload or more memory

What LLMs Can iMac 24" M3 (24 GB) Run?

293 models · 37 run great · 56 run well

Featured only

Score: model quality, 100 = average model. Fit: how well it runs on this hardware, S best to F won't fit. Ordered by quality, recency and Fit. How ranking works

Showing compatibility for iMac 24" M3 (24 GB)

LLM models compatible with iMac 24" M3 (24 GB) — ranked by quality, recency and Fit
ModelVRAMScoreFit
Qwen3 VL 4B Instruct
4.4B·Q4_K_M·22.8 t/s·262K ctx
4.5 GBB63, Decent
SmolVLM Instruct
2.2B·Q4_K_M·35.0 t/s·16K ctx
4.9 GBA73, Runs well
Qwen3.5 2B Base
2.3B·Q4_K_M·40.5 t/s·262K ctx
1.9 GBA75, Runs well
Falcon H1 7B Instruct
7.6B·Q4_K_M·14.2 t/s·262K ctx
6.3 GBB53, Decent
Olmo 3.1 32B Instruct
32.2B·Q4_K_S·3.8 t/s·66K ctx
20.3 GBF10, Won't fit
Qwen3 4B Instruct 2507
4.0B·Q4_K_M·24.7 t/s·262K ctx
4.2 GBA65, Runs well
Dots.mocr
3.0B·Q4_K_M·32.9 t/s·131K ctx
2.6 GBA72, Runs well
Qwen3.5 4B Base
4.7B·Q4_K_M·22.0 t/s·262K ctx
3.4 GBB62, Decent
Qwen3 VL 2B Instruct
2.1B·Q4_K_M·39.6 t/s·262K ctx
3.5 GBA75, Runs well
Phi 4 Reasoning
14.7B·Q4_K_M·7.5 t/s·33K ctx
12.5 GBB45, Decent
NVIDIA Nemotron Parse 2.0
903M·BF16·36.0 t/s
3.4 GBA73, Runs well
LightOnOCR 3 1B
1.0B·Q4_K_M·70.3 t/s·16K ctx
1.8 GBS86, Runs great
LFM2 VL 1.6B
1.6B·Q4_K_M·54.3 t/s·128K ctx
1.5 GBA81, Runs well
TinyLlama 1.1B Chat v1.0
1.1B·Q4_K_M·71.0 t/s·2K ctx
1.0 GBS86, Runs great
Granite 4.0 H Small
32.2B·IQ4_XS·13.1 t/s·131K ctx
20.3 GBD22, Barely runs
Granite 4.0 1B
1.6B·Q4_K_M·49.4 t/s·131K ctx
2.6 GBA79, Runs well

iMac 24" M3 (24 GB) has 20.5 GB of memory for models. In the ranking below, Qwen3.8 27B leads at Q4_K_M: it needs 17.9 GB (87% of that memory) and generates about 4.1 tokens per second. 37 of the 293 featured models earn a Fit S here, meaning they load with room for context and run fast. Decode speed is set mostly by memory bandwidth (102 GB/s), so smaller and mixture-of-experts models are noticeably quicker than dense models of the same quality. 70B-class models need about 46 GB at Q4_K_M, more than the 20.5 GB available, so they require offloading layers to system RAM or a larger-memory setup.

Runs Well

  • GPT OSS 20B (20.9B at Q4_K_M, ~24.4 tok/s)
  • Ling 3.0 Tiny (7.9B at Q4_K_M, ~56.1 tok/s)
  • MiniCPM5 2B (2.5B at Q4_K_M, ~37.7 tok/s)
  • Qwen3.5 2B (2.3B at Q4_K_M, ~40.5 tok/s)
  • LFM2.5 8B A1B (8.5B at Q4_K_M, ~50 tok/s)

Challenging

  • Qwen3.8 27B (27.8B at Q4_K_M, ~4.1 tok/s) fits but uses 87% of memory, so keep context short
  • Gemma 4 26B A4B IT (25.8B at Q4_K_M, ~22.6 tok/s) fits but uses 80% of memory, so keep context short
  • Qwen3.6 35B A3B (36.0B at IQ4_XS, ~22.6 tok/s) fits but uses 97% of memory, so keep context short
  • 70B-class models need ~46 GB at Q4_K_M, so they need CPU offload or more memory
  • 120B-class models need ~77 GB at Q4_K_M, so they need CPU offload or more memory

iMac 24" M3 (24 GB) Specifications

Brand
Apple
Chip
M3
Type
Desktop
Unified Memory
24 GB
Memory Bandwidth
102.4 GB/s
GPU Cores
10
CPU Cores
8
Neural Engine
18.0 TOPS
Release Date
2023-11-07

Get Started

Ollama (Recommended)

Runs Qwen3.8 27B on Q4_K_M; this is our top choice here.

$curl -fsSL https://ollama.com/install.sh | sh
$ollama run hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_M

LM Studio

LM Studio

Download LM Studio, search for "Qwen3.8 27B", and run it with one click.

Prompt Processing

Estimated for Qwen3.8 27B, the compute-bound phase that reads your prompt before the first reply token appears.

25.2tok/s prefill

Short chat

20.3 s

512 tok prompt

Long chat

163 s

4,096 tok prompt

Document / codebase

1300 s

32,768 tok prompt

Prefill is compute-bound and a different number from the decode tok/s shown elsewhere on this page — how prompt processing works →

Performance figures are estimates calibrated as of 2026-09-21 — see calibration basis →

What to do next with iMac 24" M3 (24 GB)

Which model to run first, a faster option with the same memory, and what more memory unlocks. Computed from the rankings and specs above.

Frequently Asked Questions

Can iMac 24" M3 (24 GB) run Qwen3.8 27B?

Yes. The iMac 24" M3 (24 GB) with 24 GB unified memory can run Qwen3.8 27B (Q4_K_M, 17.9 GB, 87% of memory). It is also the table's best pick, at ~4.1 tok/s. 37 of the 293 featured models get a Fit of S (runs great) here. The largest featured model that fits at Q4 or better is Qwen3.6 35B A3B (36.0B at IQ4_XS). 70B-class models need around 46 GB at Q4_K_M, meaning they need CPU offloading or extra memory beyond what's available in 20.5 GB. Check the compatibility table above for the full list with Fit, VRAM usage and estimated speed. Models are checked against the 20.5 GB available to AI (that is, the 24 GB of RAM minus roughly 3.5 GB for macOS), while Apple Silicon's unified memory allows the GPU to draw from that same pool without copying data.

How much memory is available for AI on iMac 24" M3 (24 GB)?

The iMac 24" M3 (24 GB) has 24 GB unified memory. After macOS reserves ~3.5 GB for the operating system, approximately 20.5 GB is available for AI models. Model rankings here use that 20.5 GB limit instead of the total 24 GB. Unlike discrete GPUs where VRAM is separate from system RAM, a unified-memory device shares one memory pool between the CPU and GPU — this means no data copying overhead, but you share memory with macOS and open apps.

Is iMac 24" M3 (24 GB) good for AI?

With 24 GB unified memory and 102.4 GB/s bandwidth, the iMac 24" M3 (24 GB) is solid for running local AI models. Models that run well include GPT OSS 20B (20.9B at Q4_K_M, ~24.4 tok/s); Ling 3.0 Tiny (7.9B at Q4_K_M, ~56.1 tok/s); MiniCPM5 2B (2.5B at Q4_K_M, ~37.7 tok/s). Mid-size models run at good quality, and Metal acceleration keeps interactive chat smooth.

What's the best model for iMac 24" M3 (24 GB)?

For the iMac 24" M3 (24 GB), the best pick right now is Qwen3.8 27B at ~4.1 tok/s. Also running well: GPT OSS 20B (20.9B at Q4_K_M, ~24.4 tok/s); Ling 3.0 Tiny (7.9B at Q4_K_M, ~56.1 tok/s); MiniCPM5 2B (2.5B at Q4_K_M, ~37.7 tok/s). The best choice depends on your use case: coding assistants benefit from code-tuned models, general chat from instruction-tuned ones. The list is ranked by quality, recency and Fit.

How fast is iMac 24" M3 (24 GB) for AI inference?

With 102.4 GB/s memory bandwidth, the iMac 24" M3 (24 GB) achieves approximately 16 tok/s on a 7B model at Q4_K_M — that's functional for interactive use. A 14B model runs at ~8 tok/s. In the ranking, the top pick Qwen3.8 27B runs at ~4.1 tok/s. Apple Silicon achieves high efficiency (~70%) thanks to unified memory — there's no PCIe bottleneck between CPU and GPU.

= (102.4 GB/s ÷ model GB) × efficiency

Apple Silicon achieves ~70% bandwidth efficiency thanks to and Metal acceleration.

Estimated speed on iMac 24" M3 (24 GB)

~4 tok/s
~23 tok/s
~23 tok/s
~11 tok/s

Real-world results typically within ±20%.

Learn more about tok/s estimation →

Can I run AI offline on iMac 24" M3 (24 GB)?

Yes — once you download a model, it runs entirely on the iMac 24" M3 (24 GB) without internet. Applications like Ollama and LM Studio make it straightforward to download, manage, and run models locally. All your conversations stay private on your device with zero data sent to external servers. This is one of the key advantages of local AI: complete privacy, no API costs, and no rate limits.