Apple · M6 · Desktop

Best AI Models for iMac 24" M6 (16 GB)

Runs 9B models well; 14B only just fits in 12.5 GB, and 27–31B doesn't fit.

16 GB unified12.5 GB for models153.6 GB/s16 TFLOPS FP162026

Buy$1,499

Memory

16 GB$1,499 24 GB$1,699 32 GB$2,099

Same chip in

iMac 24"$1,499 Mac Mini$899 MacBook Pro 14"$1,999

What LLMs can the iMac 24" M6 run?

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 16.9 t/s	16.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 33.0 t/s	33.0 tok/s	Q4_K_M · 3.4 GB
3	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 17.6 t/s	17.6 tok/s	Q4_K_M · 7.3 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 37.9 t/s	37.9 tok/s	Q4_K_M · 5.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 74.1 t/s	74.1 tok/s	Q4_K_M · 5.5 GB

#	Model	Speed	Coding Score	Quant · Memory
1	Llama 3.1 8B InstructMetaHow to run → Q4_K_M · 7.9 GB · 20.3 t/s	20.3 tok/s		Q4_K_M · 7.9 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 16.9 t/s	16.9 tok/s	overall	Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 33.0 t/s	33.0 tok/s	overall	Q4_K_M · 3.4 GB
4	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 74.1 t/s	74.1 tok/s		Q4_K_M · 5.5 GB
5	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 20.2 t/s	20.2 tok/s		Q4_K_M · 5.6 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 16.9 t/s	16.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 19.5 t/s	19.5 tok/s	Q4_K_M · 7.6 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 20.3 t/s	20.3 tok/s	Q4_K_M · 7.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 37.9 t/s	37.9 tok/s	Q4_K_M · 5.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 74.1 t/s	74.1 tok/s	Q4_K_M · 5.5 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 16.9 t/s	16.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 33.0 t/s	33.0 tok/s	Q4_K_M · 3.4 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 20.3 t/s	20.3 tok/s	Q4_K_M · 7.9 GB
4	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 74.1 t/s	74.1 tok/s	Q4_K_M · 5.5 GB
5	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 20.2 t/s	20.2 tok/s	Q4_K_M · 5.6 GB

#	Model	Speed ↓	Quant · Memory
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 33.0 t/s	33.0 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 74.1 t/s	74.1 tok/s	Q4_K_M · 5.5 GB
3	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 20.2 t/s	20.2 tok/s	Q4_K_M · 5.6 GB
4	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 19.5 t/s	19.5 tok/s	Q4_K_M · 7.6 GB
5	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 16.9 t/s	16.9 tok/s	Q4_K_M · 6.6 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 16.9 t/s	16.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 33.0 t/s	33.0 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 37.9 t/s	37.9 tok/s	Q4_K_M · 5.0 GB
4	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 17.3 t/s	17.3 tok/s	Q4_K_M · 6.5 GB
5	MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 84.0 t/s	84.0 tok/s	Q4_K_M · 1.6 GB

See all 283 models on the iMac 24" M6 →Bars = traction for models without a Score yet

About the iMac 24" M6 (16 GB)

The iMac 24" M6 is one of the fastest 16 GB machines: it runs 9B models well. Among 16 GB machines, only the M1 Pro and M2 Pro write faster. macOS keeps about 3.5 GB, leaving 12.5 GB for models. With 16 TFLOPS it reads long prompts faster than most 16 GB machines: a 4K-token prompt takes 25 s. At its $1,499 MSRP it gives 11.3 tok/s per $1,000, 5th of the 8 machines compared here.

Speed in 16 GB#3154 GB/s

Prompt reading#216 TFLOPS

For models12.5 GBmacOS keeps 3.5 GB

ChipM6released 2026

iMac 24" M6 strengths and weaknesses

Strengths

Runs 7–9B models: Qwen3.5 9B at 16.9 tok/s in 6.6 GB

Weaknesses

27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 12.5 GB usable here
Little room for context: Qwen3 14B uses 11.9 of 12.5 GB usable, 0.6 GB left
Slow prompt reading: A 32K-token prompt on Qwen3.5 9B waits 3.3 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

12.5 GB of 16 GB

9B6.6 GB14B11.9 GB

For models 12.5 GBmacOS keeps 3.5 GBModel size at Q4

27–31B models need 17.9 GB at Q4, more than the 12.5 GB available. The 24 GB config fits Qwen3.8 27B →Or rent an RTX 3090 (24 GB) from $0.18/hr →

Speed per dollar and per watt

NewUsed

On Qwen3.5 9B (9B params) at Q4_K_M. New means a shop price, either a street quote or the maker's own price; used is compared with used. The last two columns are the speed you get per $1,000 of price and per 100 W of power; higher is better. The iMac 24" M6 has no current new price, so it is shown at its MSRP.

Machine	New price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 509032 GB	about $5,502	183	33.3	31.8
Mac Mini M616 GB	about $899	16.9	18.8	–
Mac Mini M4 Pro24 GB	about $1,599	30.0	18.8	21.4
Mac Studio M4 Max36 GB	about $2,499	45.1	18.0	31.1
iMac 24" M616 GB	about $1,499	16.9	11.3	–
iMac 24" M624 GB	about $1,699	18.7	11.0	–
iMac 24" M632 GB	about $2,099	18.7	8.9	–
MacBook Pro 14" M616 GB	about $1,999	16.9	8.5	–

Machine	Used price	tok/s	tok/s per $1,000	tok/s per 100 W
RTX 409024 GBBest used value	about $3,000	103	34.3	22.9
RTX 509032 GB	about $7,000	183	26.2	31.8
Mac Studio M4 Max36 GB	about $2,000	45.1	22.6	31.1

Cost per token: the iMac 24" M6 against 16–36 GB machines and GPUs

On Qwen3.5 9B (9B params, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.

NewUsed

Speed$ per 1M tokens

≤16 GB24–36 GBthis desktopat MSRP

Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power

$5.63

Machine, MSRP: $5.63
Power: not published

3-year cost of ownership$1,499

Or rent an RTX 5080 in the cloud$0.20/hr

Renting costs as much as buying after ≈7,600 hours (≈5.2 years at 4 h a day).

Power$/kWhUseh/dayKeepyears

Each dot is a machine or GPU; hover or tap it for its numbers, click to open it. Machines without a price for the chosen basis are left out. Machines without a published power figure are left out of Per watt and costed without power. How we calculate cost per token

Similar devices and alternatives

Other memory sizes of the same machine first, then machines and GPUs people weigh against it, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

Same chip, 8 GB more memory for $200 moreiMac 24" M6 (24 GB)Apple · 20.5 GB for models · M6

▲ 11% speed▲ $200 more▲ 8 GB$1,699

Same family Same chip, 2× the memory for $600 moreiMac 24" M6 (32 GB)Apple · 28.5 GB for models · M6

▲ 11% speed▲ $600 more▲ 16 GB$2,099

Same family 78% faster, 8 GB more memoryMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro

▲ 78% speed▲ 8 GB$1,599

167% faster, 20 GB more memoryMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 167% speed▲ 20 GB$2,499

Reads prompts 23× faster, 24 GB for modelsRTX 4090NVIDIA · 24 GB VRAM · GPU

▲ 23× prompts▲ 510% speed▲ 11.5 GB$1,599rent $0.34/hr

Reads prompts 30× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU

▲ 30× prompts▲ 983% speed▲ 19.5 GB$5,502rent $0.50/hr

iMac 24" M6 tokens per second by model size

Output speed depends on memory bandwidth (154 GB/s). Grey rows need more than the 12.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
16.9tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
11.3tok/s
27–31BQwen3.8 27B · not at 4-bit
needs 17.9 GB
35B MoEQwen3.6 35B A3B · not at 4-bit
needs 22.0 GB
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

Chip generations: writing vs compute

M1 → M5

Writing speed (tok/s)Compute (TFLOPS FP16)

Writing speed follows memory bandwidth and barely moved: 7.5 to 16.8 tok/s since the M1. Compute, which sets how fast prompts are read, grew 3.1×. Indexed to the M1; speeds on Qwen3.5 9B, same 16 GB.

All 988 models on the iMac 24" M6

Featured only

Best quant that fits in 12.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with iMac 24" M6 (16 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen2.5 Omni 7B10.7BChat Q4_K_M·15.2 t/s	Q4_K_M	9.9 GB79%	15.2 t/s	—	B55, Decent
Pythia 1.4B1.5BChat Q4_K_M·107.5 t/s	Q4_K_M	1 GB8%	107.5 t/s	2K	S92, Runs great
Codegen 350M Mono350MChatCode FP16·139.6 t/s	FP16	0.8 GB6%	139.6 t/s	2K	S96, Runs great
Phi 1 51.4BChatCode Q4_K_M·114.4 t/s	Q4_K_M	0.9 GB8%	114.4 t/s	2K	S94, Runs great
Starling LM 7B Beta7.2BChat Q4_K_M·21.9 t/s	Q4_K_M	5.7 GB46%	21.9 t/s	8K	B62, Decent
Openchat 3.5 01067.2BChat Q4_K_M·21.9 t/s	Q4_K_M	5.7 GB46%	21.9 t/s	8K	B62, Decent
LFM2 350M Extract354MChatFunctions Q4_K_M·185.4 t/s	Q4_K_M	0.8 GB6%	185.4 t/s	128K	S99, Runs great
MobileLLaMA 1.4B Chat1.4BChat Q4_K_M·69.8 t/s	Q4_K_M	1.5 GB12%	69.8 t/s	2K	S86, Runs great
Llama 3.1 8B Lexi Uncensored v28.0BChat Q4_K_M·19.9 t/s	Q4_K_M	7.3 GB58%	19.9 t/s	131K	B60, Decent
Llama 3.1 8B8.0BChat Q4_K_M·20.3 t/s	Q4_K_M	7.9 GB63%	20.3 t/s	—	B60, Decent
Nidum Gemma 2B Uncensored2.5BChat Q4_K_M·58.4 t/s	Q4_K_M	1.9 GB16%	58.4 t/s	8K	A83, Runs well
AREX 227.4BVisionFunctionsReasoning IQ3_XS·8.9 t/s	IQ3_XS	12.5 GB100%	8.9 t/s	262K	D15, Barely runs
Yi Coder 9B Chat8.8BChatCode Q4_K_M·18.5 t/s	Q4_K_M	7.2 GB58%	18.5 t/s	131K	B58, Decent
Holo4 27B27.4BVisionFunctions IQ3_XS·8.9 t/s	IQ3_XS	12.5 GB100%	8.9 t/s	262K	D15, Barely runs
Qwen3 Code Reasoning 4B4BChatCodeReasoning Q4_K_M·37.2 t/s	Q4_K_M	4.2 GB34%	37.2 t/s	262K	A74, Runs well

iMac 24" M6 specs

Specs

Chip: M6
CPU cores: 10
GPU cores: 10
Unified memory: 16 GB
For models: 12.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 153.6 GB/s
FP16 (dense): 16 TFLOPS
Neural Engine: 76 TOPS
Released: 2026-11-06
MSRP: $1,499

iMac 24" M6 FAQ

Is the iMac 24" M6 (16 GB) worth it for local LLMs in 2026?

At its $1,499 MSRP it gives 11.3 tok/s per $1,000 on Qwen3.5 9B, 5th of the 8 machines compared here. It runs 9B models well; 14B only just fits in 12.5 GB, and 27–31B doesn't fit.

How much memory is available for AI on the iMac 24" M6 (16 GB)?

About 12.5 GB of the 16 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the iMac 24" M6 (16 GB) can run?

GPT OSS 20B (20.9B) is the largest at 4-bit or better: at Q4_K_S it uses 12.4 GB, 99% of the available memory, and runs at about 36.4 tok/s.

Can the iMac 24" M6 (16 GB) run Qwen3.5 9B?

Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of the 12.5 GB available, and it is the best model that runs well on this machine.

Can the iMac 24" M6 (16 GB) run 27–31B models?

No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 12.5 GB available.

How long does the iMac 24" M6 (16 GB) take to read a long prompt?

On Qwen3.5 9B, about 25 s for a 4K-token prompt and 3.3 min for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the iMac 24" M6?

An RTX 5080 (16 GB) rents from $0.20/hr. Renting costs as much as buying after ≈7,600 hours (≈5.2 years at 4 h a day).

12 GB GPUs All Macs Desktops & mini PCs Mac Mini M2 Pro MacBook Pro 14" M1 Pro MacBook Pro 14" M2 Pro MacBook Pro 16" M1 Pro MacBook Pro 16" M2 Pro Best coding LLMs All hardware