Apple · M6 · Desktop

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

Runs 9B models well and fits 35B MoE; 14B and 27–31B fit but are slow (13 and 7 tok/s), and 70B doesn't fit in 20.5 GB.

24 GB unified20.5 GB for models170 GB/s16 TFLOPS FP162026

Buy$1,699

Memory

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

Same chip in

iMac 24"$1,699 Mac Mini$1,099 MacBook Pro 14"$2,199

What LLMs can the iMac 24" M6 run?

#	Model	Speed	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 16.5 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s	18.7 tok/s	Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 36.5 t/s	36.5 tok/s	Q4_K_M · 3.4 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s	48.1 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed	Coding Score	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s		Q4_K_M · 16.5 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s		Q4_K_M · 13.1 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 22.5 t/s	22.5 tok/s		Q4_K_M · 7.9 GB
4	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s	18.7 tok/s	overall	Q4_K_M · 6.6 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s	48.1 tok/s		Q4_K_M · 15.0 GB

#	Model	Speed	Quant · Memory
1	Gemma 4 26B A4B ITGoogleHow to run → Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 16.5 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s	18.7 tok/s	Q4_K_M · 6.6 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
4	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 21.6 t/s	21.6 tok/s	Q4_K_M · 7.6 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s	48.1 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed	Quant · Memory
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 18.7 t/s	18.7 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 36.5 t/s	36.5 tok/s	Q4_K_M · 3.4 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 22.5 t/s	22.5 tok/s	Q4_K_M · 7.9 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s	48.1 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed ↓	Quant · Memory
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 13.1 GB
2	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 48.1 t/s	48.1 tok/s	Q4_K_M · 15.0 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 36.5 t/s	36.5 tok/s	Q4_K_M · 3.4 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 34.4 t/s	34.4 tok/s	Q4_K_M · 16.5 GB
5	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 18.7 t/s	18.7 tok/s	Q4_K_M · 6.6 GB

See all 322 models on the iMac 24" M6 →Bars = traction for models without a Score yet

About the iMac 24" M6 (24 GB)

The iMac 24" M6 is a mid-range 24 GB desktop: it runs 9B models well and fits 35B MoE. Among 24 GB machines, only the M5 Pro and M4 Pro write faster. macOS keeps about 3.5 GB, leaving 20.5 GB for models. With 16 TFLOPS it reads long prompts faster than most 24 GB machines: a 4K-token prompt takes 11 s. At its $1,699 MSRP it gives 11.0 tok/s per $1,000, 6th of the 8 machines compared here.

Speed in 24 GB#3170 GB/s

Prompt reading#216 TFLOPS

For models20.5 GBmacOS keeps 3.5 GB

ChipM6released 2026

iMac 24" M6 strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 33.5 tok/s in 19.8 GB

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 20.5 GB usable here
Slow on large dense models: Qwen3.8 27B at 6.8 tok/s
Slow prompt reading: A 32K-token prompt on Gemma 4 26B A4B IT waits 1.5 min for the first token
No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

20.5 GB of 24 GB

9B6.6 GB14B11.9 GB27–31B17.9 GB35B MoE19.8 GB

9B6.6 GB14B11.9 GB35B MoE19.8 GB

For models 20.5 GBmacOS keeps 3.5 GBModel size at Q4

70B models need 51.3 GB at Q4, more than the 20.5 GB available. The 32 GB config fits Qwen3.8 27B →Or rent an A100 (80 GB) from $1.06/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
Mac Mini M4 Pro24 GB	about $1,599	30.0	18.8	21.4
Mac Mini M624 GB	about $1,099	18.7	17.0	–
MacBook Pro 14" M4 Pro24 GB	about $1,999	30.0	15.0	–
MacBook Pro 16" M4 Pro24 GB	about $2,499	30.0	12.0	–
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" M624 GB	about $2,199	18.7	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

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 less memory for $200 lessiMac 24" M6 (16 GB)Apple · 12.5 GB for models · M6

▼ 10% speed▼ $200 less▼ 8 GB$1,499

Same family Same chip, 8 GB more memory for $400 moreiMac 24" M6 (32 GB)Apple · 28.5 GB for models · M6

same speed▲ $400 more▲ 8 GB$2,099

Same family 60% faster, same memoryMac Mini M4 Pro (24 GB)Apple · 20.5 GB for models · M4 Pro

▲ 60% speedsame memory$1,599

141% faster, 12 GB more memoryMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max

▲ 141% speed▲ 12 GB$2,499

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

▲ 23× prompts▲ 451% speed▲ 3.5 GB$1,599rent $0.34/hr

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

▲ 30× prompts▲ 879% speed▲ 11.5 GB$5,502rent $0.50/hr

iMac 24" M6 tokens per second by model size

Output speed depends on memory bandwidth (170 GB/s). Grey rows need more than the 20.5 GB available.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
18.7tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
12.5tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB slow
6.8tok/s
35B MoEQwen3.6 35B A3B · IQ4_XS · 19.8 GB tight · IQ4_XS
33.5tok/s
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 16.9 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 1142 models on the iMac 24" M6

Featured only

Best quant that fits in 20.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with iMac 24" M6 (24 GB) — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
OLMo 2 0425 1B1.5BChat Q4_K_M·81.5 t/s	Q4_K_M	1.7 GB8%	81.5 t/s	4K	S88, Runs great
Instella 3B3.1BChat BF16·16.3 t/s	BF16	8.0 GB39%	16.3 t/s	4K	B56, Decent
LFM2 8B A1B8.3BChat Q4_K_M·75.3 t/s	Q4_K_M	5.5 GB27%	75.3 t/s	128K	S86, Runs great
Phi 4 Mini Instruct3.8BChatCodeFunctions Q4_K_M·41.5 t/s	Q4_K_M	4.8 GB23%	41.5 t/s	131K	A76, Runs well
Gemma 3n E2B IT5.4BVision Q4_K_M·33.1 t/s	Q4_K_M	5.9 GB29%	33.1 t/s	—	A72, Runs well
Qwen2 VL 2B Instruct2.2BVision Q4_K_M·70.8 t/s	Q4_K_M	2.1 GB10%	70.8 t/s	33K	S86, Runs great
MiniCPM V 4 58.7BVisionFunctions Q4_K_M·20.4 t/s	Q4_K_M	7.9 GB39%	20.4 t/s	41K	B60, Decent
Smol Llama 101M GQA101MChat Q4_K_M·321.6 t/s	Q4_K_M	0.4 GB2%	321.6 t/s	1K	S100, Runs great
Qwen3 32B32.8BChatFunctions Q3_K_L·6.8 t/s	Q3_K_L	19.8 GB96%	6.8 t/s	41K	D20, Barely runs
Gemma 3 4B Pt4.3BVision Q4_K_M·41.9 t/s	Q4_K_M	5 GB24%	41.9 t/s	—	A76, Runs well
TinyLlama 1.1B Chat V0.61.1BChat Q4_K_M·117.8 t/s	Q4_K_M	1.0 GB5%	117.8 t/s	2K	S94, Runs great
Lucie 7B6.7BChat Q4_K_M·25.9 t/s	Q4_K_M	6.5 GB32%	25.9 t/s	32K	A66, Runs well
Phi 4 Mini Reasoning3.8BChatMathCodeReasoningFunctions Q4_K_M·41.5 t/s	Q4_K_M	4.8 GB23%	41.5 t/s	131K	A76, Runs well
SmolLM3 3B Base3.1BChat Q4_K_M·51.7 t/s	Q4_K_M	3.4 GB16%	51.7 t/s	66K	A80, Runs well
Qwen2.5 Coder 32B Instruct32.8BChatCodeFunctions IQ3_M·7.6 t/s	IQ3_M	19.3 GB94%	7.6 t/s	33K	D24, Barely runs

iMac 24" M6 specs

Specs

Chip: M6
CPU cores: 10
GPU cores: 10
Unified memory: 24 GB
For models: 20.5 GB (macOS keeps 3.5 GB)
Memory bandwidth: 170 GB/s
FP16 (dense): 16 TFLOPS
Neural Engine: 76 TOPS
Released: 2026-11-06
MSRP: $1,699

iMac 24" M6 FAQ

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

At its $1,699 MSRP it gives 11.0 tok/s per $1,000 on Qwen3.5 9B, 6th of the 8 machines compared here. It runs 9B models well and fits 35B MoE; 14B and 27–31B fit but are slow (13 and 7 tok/s), and 70B doesn't fit in 20.5 GB.

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

About 20.5 GB of the 24 GB. macOS keeps roughly 3.5 GB for itself and other apps.

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

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at IQ4_XS it uses 19.8 GB, 97% of the available memory, and runs at about 33.5 tok/s.

Can the iMac 24" M6 (24 GB) run Gemma 4 26B A4B IT?

Yes. Gemma 4 26B A4B IT fits at Q4_K_M, using 16.5 GB of the 20.5 GB available, and it is the best model that runs well on this machine.

Can the iMac 24" M6 (24 GB) run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 20.5 GB available.

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

On Gemma 4 26B A4B IT, about 11 s for a 4K-token prompt and 1.5 min for a 32K-token document before the first word appears.

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

An RTX 5090 (32 GB) rents from $0.46/hr. Renting costs as much as buying after ≈3,700 hours (≈2.5 years at 4 h a day).

16 GB GPUs All Macs Desktops & mini PCs Mac Mini M5 Pro MacBook Pro 14" M5 Pro MacBook Pro 16" M5 Pro Mac Mini M6 Best coding LLMs All hardware