Unified memory · Apple

What AI models can an Apple M2 16GB run?

16 GB covers almost everything people actually use day to day, including the 24B to 32B class that most reviewers consider the practical ceiling for a single consumer card. Memory is shared with the CPU, so the practical ceiling is lower than the sticker number: macOS hands roughly three quarters of it to the GPU by default.

Memory16 GB

Bandwidth100 GB/s

Usable for a model10.72 GB

Runtime backendMETAL

The short answer

Assuming an 8k context window and default settings, these are the models worth downloading first.

Best all-rounder

Qwen3.5 9B

Q5_K_M · 7.07 GB · about 11.3 tokens/s

Best for code

Qwen2.5 Coder 7B Instruct

Q6_K · 6.62 GB · about 11.6 tokens/s

Largest that still runs well

Mistral Nemo Instruct 2407

12.25B parameters · Q3_K_M · about 10.4 tokens/s

Fastest useful answer

LFM2.5 8B A1B

about 23.9 tokens/s · 8.78 GB

See how fast it feels

Apple M2 16GB running Qwen3.5 9B at Q5_K_M

Wait for the first word9.1 s

Then writes at11.3 tok/s

Whole answer24 s

YouWhy does my model use more memory when the conversation gets longer?

Model

Simulated from our estimate at a 512-token question, not a recording. Assumes nothing else is competing for the GPU.

Where it sits

The GPU can use about 10.72 GB of this machine's 16 GB by default, so for planning it behaves like a 8 GB card with different bandwidth. The 8 GB guide explains what that tier runs and where it runs out, and the bandwidth guide explains why 100 GB/s decides how fast it answers.

We do not track a price for this device, so it does not appear in the budget tools.

Every model, scored on this device

Each row uses the highest-quality quantization that both fits and stays conversational. Speed is a single-stream estimate at 8k context.

Model	Params	Verdict	Download	Memory used	Speed	Max context
Qwen3.5 9B Qwen	9.65B	Runs well	Q5_K_M	7.07 GB	11.3 t/s	64k
Gemma 4 E4B Instruct Gemma	8B	Runs well	Q6_K	6.58 GB	10.9 t/s	128k
Qwen2.5 VL 7B Instruct Qwen	8.29B	Runs well	Q6_K	7.13 GB	10.7 t/s	64k
Qwen3 8B Qwen	8.19B	Runs well	Q5_K_M	6.93 GB	11.1 t/s	32k
LFM2.5 8B A1B Liquid	8.47B (1.57B active)	Runs well	Q8_0	8.78 GB	23.9 t/s	64k
Qwen2.5 7B Instruct Qwen	7.62B	Runs well	Q6_K	6.62 GB	11.6 t/s	32k
Gemma 4 E2B Instruct Gemma	5.12B	Runs well	Q8_0	5.41 GB	13.3 t/s	128k
Qwen3.5 4B Qwen	4.66B	Runs well	Q8_0	5.24 GB	13.8 t/s	128k
Granite 4.1 8B Granite	8.79B	Runs well	Q4_K_M	6.57 GB	11 t/s	32k
Qwen2.5 Coder 7B Instruct Qwen	7.62B	Runs well	Q6_K	6.62 GB	11.6 t/s	32k
Llama 3.1 8B Instruct Llama	8.03B	Runs well	Q6_K	7.51 GB	10.1 t/s	32k
Gemma 4 12B Instruct Gemma	11.96B	Runs well	Q3_K_M	7.13 GB	10.1 t/s	32k
Mistral 7B Instruct V0.3 Mistral	7.25B	Runs well	Q6_K	6.91 GB	10.6 t/s	32k
Internlm3 8B Instruct InternLM	8.8B	Runs well	Q6_K	7.47 GB	10.2 t/s	32k
Gemma 3 12B Instruct Gemma	12.19B	Runs well	Q3_K_M	6.73 GB	10.7 t/s	64k
Gemma 3 4B Instruct Gemma	4.3B	Runs well	Q8_0	4.88 GB	14.9 t/s	128k
Mistral 7B Instruct V0.2 Mistral	7.24B	Runs well	Q6_K	6.9 GB	10.6 t/s	32k
Qwen3 4B Qwen	4.02B	Runs well	Q8_0	5.43 GB	13.3 t/s	32k
Qwen2.5 3B Instruct Qwen	3.09B	Runs well	Q8_0	3.65 GB	20.4 t/s	32k
OLMo 3 7B Instruct OLMo	7.3B	Runs well	Q4_K_M	6.98 GB	10.7 t/s	32k
Gemma 2 9B Instruct Gemma	9.24B	Runs well	IQ4_XS	6.9 GB	10.4 t/s	8k
Mistral Nemo Instruct 2407 Mistral	12.25B	Runs well	Q3_K_M	7.24 GB	10.4 t/s	16k
Granite 4.1 3B Granite	3.4B	Runs well	Q8_0	4.31 GB	17 t/s	64k
LFM2.5 2.6B Liquid	2.7B	Runs well	Q8_0	3.11 GB	24.3 t/s	128k
Phi 4 Mini Instruct Phi	3.84B	Runs well	Q8_0	5.14 GB	14.2 t/s	32k
Llama 3.2 3B Instruct Llama	3.21B	Runs well	Q8_0	4.39 GB	16.8 t/s	64k
Qwen3.5 2B Qwen	2.27B	Runs great	Q8_0	2.67 GB	28.8 t/s	256k
Phi 3 Mini 4k Instruct Phi	3.82B	Runs well	Q8_0	4.87 GB	15.3 t/s	4k
Gemma 2 2B Instruct Gemma	2.61B	Runs well	Q8_0	3.51 GB	21.3 t/s	8k
Starcoder2 3B StarCoder	3.03B	Runs well	Q8_0	3.46 GB	22.9 t/s	16k

Show the other 56 models

Qwen3 1.7B	2.03B	Runs well	Q8_0	3.19 GB	23.6 t/s	32k
DeepSeek Coder 7B Instruct V1.5	6.91B	Runs well	Q3_K_M	7.27 GB	10.1 t/s	4k
DeepSeek R1 Distill Qwen 1.5B	1.78B	Runs great	Q8_0	2.27 GB	38.9 t/s	128k
Qwen2.5 1.5B Instruct	1.54B	Runs great	Q8_0	2.03 GB	39 t/s	32k
SmolLM2 1.7B	1.71B	Runs well	Q8_0	3.5 GB	21.3 t/s	8k
OLMo 2 0425 1B	1.48B	Runs great	Q8_0	2.77 GB	30.1 t/s	4k
Llama 3.2 1B Instruct	1.24B	Runs great	Q8_0	1.79 GB	46 t/s	128k
LFM2.5 1.2B Instruct	1.17B	Runs great	Q8_0	1.56 GB	60.8 t/s	64k
Gemma 3 1B Instruct	1B	Runs great	Q8_0	1.32 GB	65.4 t/s	32k
Qwen3.5 0.8B	0.87B	Runs great	Q8_0	1.25 GB	69.9 t/s	256k
Qwen3 0.6B	0.75B	Runs great	Q8_0	1.89 GB	42 t/s	32k
Qwen2.5 0.5B Instruct	0.49B	Runs great	Q8_0	0.85 GB	117.5 t/s	32k
LFM2.5 350M	0.35B	Runs great	Q8_0	0.71 GB	181.9 t/s	64k
Qwen3.5 35B A3B	35.95B	Fits only at 2 to 3 bits	n/a	13.33 GB	31.9 t/s	n/a
GLM 4.7 Flash	31.22B	Fits only at 2 to 3 bits	n/a	11.84 GB	23.1 t/s	n/a
Qwen3 30B A3B	30.53B	Fits only at 2 to 3 bits	n/a	11.93 GB	20.5 t/s	n/a
Qwen3 Coder 30B A3B Instruct	30.53B	Fits only at 2 to 3 bits	n/a	11.93 GB	20.5 t/s	n/a
DeepSeek Coder V2 Lite Instruct	15.71B	Just fits	n/a	12.54 GB	17.1 t/s	n/a
GPT OSS 20B	20.91B	Just fits	n/a	11.81 GB	16.5 t/s	n/a
Phi 3.5 MoE Instruct	41.87B	Fits only at 2 to 3 bits	n/a	11.42 GB	15.2 t/s	n/a
Gemma 4 26B A4B Instruct	25.81B	Just fits	n/a	13.93 GB	14.8 t/s	n/a
Mixtral 8x7B Instruct V0.1	46.7B	Fits only at 2 to 3 bits	n/a	12.57 GB	9.7 t/s	n/a
DeepSeek Coder 6.7B Instruct	6.74B	Just fits	n/a	11.04 GB	6.5 t/s	n/a
Gemma 4 31B Instruct	31.27B	Fits only at 2 to 3 bits	n/a	11.2 GB	6.3 t/s	n/a
Qwen3 14B	14.77B	Just fits	n/a	12.94 GB	5.7 t/s	n/a
Qwen2.5 14B Instruct	14.77B	Just fits	n/a	13.19 GB	5.6 t/s	n/a
Qwen2.5 Coder 14B Instruct	14.77B	Just fits	n/a	13.19 GB	5.6 t/s	n/a
Granite 4.1 30B	28.87B	Fits only at 2 to 3 bits	n/a	12.66 GB	5.5 t/s	n/a
Phi 4	14.66B	Just fits	n/a	13.17 GB	5.5 t/s	n/a
Mistral Small 24B Instruct 2501	23.57B	Just fits	n/a	13.32 GB	5.4 t/s	n/a
Qwen3.5 27B	27.78B	Just fits	n/a	13.7 GB	5.3 t/s	n/a
Qwen3 32B	32.76B	Fits only at 2 to 3 bits	n/a	14.08 GB	5.1 t/s	n/a
Qwen2.5 32B Instruct	32.76B	Fits only at 2 to 3 bits	n/a	14.08 GB	5.1 t/s	n/a
Qwen2.5 Coder 32B Instruct	32.76B	Fits only at 2 to 3 bits	n/a	14.08 GB	5.1 t/s	n/a
Gemma 3 27B Instruct	27.43B	Just fits	n/a	13.99 GB	5 t/s	n/a
Codestral 22B V0.1	22.25B	Just fits	n/a	14.7 GB	4.8 t/s	n/a
Kimi K2.6	1026.88B	Will not run	n/a	578.41 GB	n/a	n/a
Kimi K2 Instruct	1026.41B	Will not run	n/a	578.15 GB	n/a	n/a
GLM 5.1	753.86B	Will not run	n/a	425.01 GB	n/a	n/a
GLM 5.2	753.33B	Will not run	n/a	424.72 GB	n/a	n/a
DeepSeek V3.2	685.4B	Will not run	n/a	386.4 GB	n/a	n/a
DeepSeek R1	684.53B	Will not run	n/a	385.92 GB	n/a	n/a
MiniMax M3	427.04B	Will not run	n/a	241.5 GB	n/a	n/a
GLM 4.5	358.34B	Will not run	n/a	204.77 GB	n/a	n/a
Qwen3 235B A22B	235.09B	Will not run	n/a	134.03 GB	n/a	n/a
MiniMax M2.5	228.7B	Will not run	n/a	130.88 GB	n/a	n/a
MiniMax M2.7	228.69B	Will not run	n/a	130.87 GB	n/a	n/a
Qwen3.5 122B A10B	125.09B	Will not run	n/a	71.01 GB	n/a	n/a
GPT OSS 120B	116.83B	Will not run	n/a	59.65 GB	n/a	n/a
GLM 4.5 Air	110.47B	Will not run	n/a	63.93 GB	n/a	n/a
Qwen3 Next 80B A3B Instruct	81.32B	Will not run	n/a	46.29 GB	n/a	n/a
Qwen3 Coder Next	79.67B	Will not run	n/a	45.37 GB	n/a	n/a
Qwen2.5 VL 72B Instruct	73.41B	Will not run	n/a	44.29 GB	n/a	n/a
Qwen2.5 72B Instruct	72.71B	Will not run	n/a	43.9 GB	n/a	n/a
Llama 3.3 70B Instruct	70.55B	Will not run	n/a	42.68 GB	n/a	n/a
Llama 3 3 Nemotron Super 49B V1	49.87B	Will not run	n/a	48.55 GB	n/a	n/a

What it will not run

43 of the 86 architectures we track are out of reach here, even at 2-bit precision.

If you want more headroom

The next steps up in memory, in order. More memory changes which models load at all; more bandwidth changes how fast they answer, so the two are worth weighing separately.

Device	Memory	Bandwidth	Models that fit
Radeon RX 7900 XT	20 GB	800 GB/s	64	Check price
GeForce RTX 4090	24 GB	1008 GB/s	69	Check price
GeForce RTX 3090 Ti	24 GB	1008 GB/s	69	Check price
Radeon RX 7900 XTX	24 GB	960 GB/s	69	Check price

Price links go to an Amazon search for the model name and are affiliate links: if you buy through one, we earn a commission at no cost to you. We do not take payment for placement, and the ordering above is by memory capacity alone.

Other devices with 16 GB

Same capacity, different speed. Once a model fits, bandwidth is what separates these.

GeForce RTX 5080

960 GB/s · NVIDIA

GeForce RTX 5070 Ti

896 GB/s · NVIDIA

GeForce RTX 5080 Laptop

768 GB/s · NVIDIA

GeForce RTX 4080 SUPER

736 GB/s · NVIDIA

GeForce RTX 4080

717 GB/s · NVIDIA

GeForce RTX 4070 Ti SUPER

672 GB/s · NVIDIA

Questions people ask about an Apple M2 16GB

How much VRAM does an Apple M2 16GB have?

The Apple M2 16GB has 16 GB of unified memory shared with the CPU, of which roughly 10.72 GB is available to a model once the operating system takes its share.

Can an Apple M2 16GB run a 70B model?

Not usefully. A 70B model needs about 45.37 GB at 4-bit and this device offers 10.72 GB.

What is the best local model for an Apple M2 16GB?

Qwen3.5 9B at Q5_K_M is the strongest all-round fit: 7.07 GB used, around 11.3 tokens per second at 8k context.