Unified memory · Apple

What AI models can an Apple M1 8GB run?

8 GB is the awkward size. It runs the 7 to 9 billion parameter class comfortably and hits a wall immediately above it, so most of the decisions here are about context length rather than model choice. 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.

Memory8 GB

Bandwidth68.25 GB/s

Usable for a model5.36 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 4B

Q6_K · 4.18 GB · about 12 tokens/s

Best for code

Qwen2.5 Coder 7B Instruct

Q4_K_M · 5.08 GB · about 10.5 tokens/s

Largest that still runs well

Internlm3 8B Instruct

8.8B parameters · IQ4_XS · about 10.4 tokens/s

Fastest useful answer

Starcoder2 3B

about 15.6 tokens/s · 3.46 GB

See how fast it feels

Apple M1 8GB running Qwen3.5 4B at Q6_K

Wait for the first word6.1 s

Then writes at12 tok/s

Whole answer21 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

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
Gemma 4 E4B Instruct Gemma	8B	Just fits	Q4_K_M	4.97 GB	10 t/s	32k
Gemma 4 E2B Instruct Gemma	5.12B	Runs well	Q6_K	4.26 GB	11.7 t/s	128k
Qwen3.5 4B Qwen	4.66B	Runs well	Q6_K	4.18 GB	12 t/s	32k
Qwen2.5 VL 7B Instruct Qwen	8.29B	Just fits	IQ4_XS	4.9 GB	10.9 t/s	16k
Qwen2.5 7B Instruct Qwen	7.62B	Just fits	Q4_K_M	5.08 GB	10.5 t/s	8k
Qwen2.5 Coder 7B Instruct Qwen	7.62B	Just fits	Q4_K_M	5.08 GB	10.5 t/s	8k
Qwen3 8B Qwen	8.19B	Just fits	Q3_K_M	5.23 GB	10.2 t/s	8k
Internlm3 8B Instruct InternLM	8.8B	Just fits	IQ4_XS	5.11 GB	10.4 t/s	8k
Qwen3 4B Qwen	4.02B	Just fits	Q6_K	4.52 GB	11.1 t/s	8k
Mistral 7B Instruct V0.3 Mistral	7.25B	Just fits	IQ4_XS	4.96 GB	10.3 t/s	8k
Llama 3.1 8B Instruct Llama	8.03B	Just fits	Q3_K_M	5.03 GB	10.5 t/s	8k
Qwen3.5 2B Qwen	2.27B	Runs well	Q8_0	2.67 GB	19.7 t/s	128k
Gemma 3 4B Instruct Gemma	4.3B	Just fits	Q8_0	4.88 GB	10.2 t/s	16k
Mistral 7B Instruct V0.2 Mistral	7.24B	Just fits	IQ4_XS	4.96 GB	10.3 t/s	8k
Qwen2.5 3B Instruct Qwen	3.09B	Runs well	Q8_0	3.65 GB	13.9 t/s	32k
LFM2.5 2.6B Liquid	2.7B	Runs well	Q8_0	3.11 GB	16.6 t/s	128k
Phi 4 Mini Instruct Phi	3.84B	Runs well	Q6_K	4.28 GB	11.8 t/s	16k
Granite 4.1 3B Granite	3.4B	Runs well	Q8_0	4.31 GB	11.6 t/s	16k
Llama 3.2 3B Instruct Llama	3.21B	Just fits	Q8_0	4.39 GB	11.5 t/s	16k
Phi 3 Mini 4k Instruct Phi	3.82B	Just fits	Q8_0	4.87 GB	10.5 t/s	4k
Qwen3 1.7B Qwen	2.03B	Runs well	Q8_0	3.19 GB	16.1 t/s	16k
Starcoder2 3B StarCoder	3.03B	Runs well	Q8_0	3.46 GB	15.6 t/s	16k
Gemma 2 2B Instruct Gemma	2.61B	Runs well	Q8_0	3.51 GB	14.5 t/s	8k
DeepSeek R1 Distill Qwen 1.5B Qwen	1.78B	Runs great	Q8_0	2.27 GB	26.5 t/s	64k
Qwen2.5 1.5B Instruct Qwen	1.54B	Runs great	Q8_0	2.03 GB	26.6 t/s	32k
OLMo 2 0425 1B OLMo	1.48B	Runs well	Q8_0	2.77 GB	20.5 t/s	4k
Llama 3.2 1B Instruct Llama	1.24B	Runs great	Q8_0	1.79 GB	31.4 t/s	64k
SmolLM2 1.7B SmolLM	1.71B	Runs well	Q8_0	3.5 GB	14.5 t/s	8k
LFM2.5 1.2B Instruct Liquid	1.17B	Runs great	Q8_0	1.56 GB	41.5 t/s	64k
Gemma 3 1B Instruct Gemma	1B	Runs great	Q8_0	1.32 GB	44.7 t/s	32k

Show the other 56 models

Qwen3.5 0.8B	0.87B	Runs great	Q8_0	1.25 GB	47.7 t/s	256k
Qwen3 0.6B	0.75B	Runs great	Q8_0	1.89 GB	28.7 t/s	32k
Qwen2.5 0.5B Instruct	0.49B	Runs great	Q8_0	0.85 GB	80.2 t/s	32k
LFM2.5 350M	0.35B	Runs great	Q8_0	0.71 GB	124.2 t/s	64k
DeepSeek Coder V2 Lite Instruct	15.71B	Fits only at 2 to 3 bits	n/a	6.14 GB	22.4 t/s	n/a
LFM2.5 8B A1B	8.47B	Just fits	n/a	6.87 GB	20.8 t/s	n/a
Gemma 4 26B A4B Instruct	25.81B	Fits only at 2 to 3 bits	n/a	7.34 GB	15.7 t/s	n/a
Qwen3.5 9B	9.65B	Just fits	n/a	5.45 GB	10.2 t/s	n/a
Granite 4.1 8B	8.79B	Just fits	n/a	6.57 GB	7.5 t/s	n/a
Qwen3 14B	14.77B	Fits only at 2 to 3 bits	n/a	6.92 GB	7.4 t/s	n/a
OLMo 3 7B Instruct	7.3B	Just fits	n/a	6.98 GB	7.3 t/s	n/a
DeepSeek Coder 6.7B Instruct	6.74B	Fits only at 2 to 3 bits	n/a	6.78 GB	7.3 t/s	n/a
Qwen2.5 14B Instruct	14.77B	Fits only at 2 to 3 bits	n/a	7.17 GB	7.2 t/s	n/a
Qwen2.5 Coder 14B Instruct	14.77B	Fits only at 2 to 3 bits	n/a	7.17 GB	7.2 t/s	n/a
Mistral Nemo Instruct 2407	12.25B	Just fits	n/a	7.24 GB	7.1 t/s	n/a
Gemma 2 9B Instruct	9.24B	Just fits	n/a	6.9 GB	7.1 t/s	n/a
Phi 4	14.66B	Fits only at 2 to 3 bits	n/a	7.19 GB	7 t/s	n/a
Mistral Small 24B Instruct 2501	23.57B	Fits only at 2 to 3 bits	n/a	7.31 GB	6.9 t/s	n/a
Gemma 4 12B Instruct	11.96B	Just fits	n/a	7.13 GB	6.9 t/s	n/a
DeepSeek Coder 7B Instruct V1.5	6.91B	Just fits	n/a	7.27 GB	6.9 t/s	n/a
Gemma 3 12B Instruct	12.19B	Just fits	n/a	7.21 GB	6.8 t/s	n/a
Mixtral 8x7B Instruct V0.1	46.7B	CPU only	n/a	27.63 GB	n/a	n/a
Phi 3.5 MoE Instruct	41.87B	CPU only	n/a	24.92 GB	n/a	n/a
Qwen3.5 35B A3B	35.95B	CPU only	n/a	20.74 GB	n/a	n/a
Qwen3 32B	32.76B	CPU only	n/a	20.83 GB	n/a	n/a
Qwen2.5 32B Instruct	32.76B	CPU only	n/a	20.83 GB	n/a	n/a
Gemma 4 31B Instruct	31.27B	CPU only	n/a	21.28 GB	n/a	n/a
GLM 4.7 Flash	31.22B	CPU only	n/a	18.28 GB	n/a	n/a
Qwen3 30B A3B	30.53B	CPU only	n/a	18.23 GB	n/a	n/a
Granite 4.1 30B	28.87B	CPU only	n/a	18.61 GB	n/a	n/a
Qwen3.5 27B	27.78B	CPU only	n/a	16.67 GB	n/a	n/a
Gemma 3 27B Instruct	27.43B	CPU only	n/a	16.93 GB	n/a	n/a
Codestral 22B V0.1	22.25B	CPU only	n/a	14.7 GB	n/a	n/a
GPT OSS 20B	20.91B	CPU only	n/a	11.81 GB	n/a	n/a
Qwen2.5 Coder 32B Instruct	32.76B	CPU only	n/a	20.83 GB	n/a	n/a
Qwen3 Coder 30B A3B Instruct	30.53B	CPU only	n/a	18.23 GB	n/a	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

52 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
GeForce RTX 3080 10GB	10 GB	760 GB/s	53	Check price
Arc B570	10 GB	380 GB/s	53	Check price
GeForce RTX 2080 Ti	11 GB	616 GB/s	57	Check price
GeForce GTX 1080 Ti	11 GB	484 GB/s	57	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 8 GB

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

GeForce RTX 3070 Ti

608 GB/s · NVIDIA

Arc A750

512 GB/s · Intel

GeForce RTX 5060 Ti 8GB

448 GB/s · NVIDIA

GeForce RTX 5060

448 GB/s · NVIDIA

GeForce RTX 3070

448 GB/s · NVIDIA

GeForce RTX 3060 Ti

448 GB/s · NVIDIA

Questions people ask about an Apple M1 8GB

How much VRAM does an Apple M1 8GB have?

The Apple M1 8GB has 8 GB of unified memory shared with the CPU, of which roughly 5.36 GB is available to a model once the operating system takes its share.

Can an Apple M1 8GB run a 70B model?

Not usefully. A 70B model needs about 45.37 GB at 4-bit and this device offers 5.36 GB.

What is the best local model for an Apple M1 8GB?

Qwen3.5 4B at Q6_K is the strongest all-round fit: 4.18 GB used, around 12 tokens per second at 8k context.