LocalLLMChecker

Unified memory · Apple

What AI models can an Apple M5 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
Bandwidth153 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

Q8_0 · 10.22 GB · about 11.8 tokens/s

Best for code

Qwen2.5 Coder 14B Instruct

Q4_K_M · 10.22 GB · about 11.1 tokens/s

Largest that still runs well

Qwen3 14B

14.77B parameters · Q4_K_M · about 11.4 tokens/s

Fastest useful answer

LFM2.5 8B A1B

about 36.6 tokens/s · 8.78 GB

See how fast it feels

Apple M5 16GB running Qwen3.5 9B at Q8_0

Wait for the first word5.3 s
Then writes at11.8 tok/s
Whole answer20 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 153 GB/s decides how fast it answers.

Our indicative price for this machine is $1,599 new, reviewed 2026-09-01. That is 1.0 GB of memory and 10 GB/s of bandwidth for every $100. Prices move, so treat these as a place to start a search and not a quote.

Devices in a similar price band, fastest memory first:

DevicePriceMemoryBandwidthBest all-round pick
Apple M1 Max 32GB $1,400 32 GB 400 GB/s Gemma 4 12B Instruct, 20.7 t/s
Apple M1 Max 64GB $1,900 64 GB 400 GB/s Qwen3.5 35B A3B, 51.8 t/s
Apple M4 Pro 24GB $1,399 24 GB 273 GB/s GPT OSS 20B, 45.1 t/s
Apple M4 Pro 48GB $1,799 48 GB 273 GB/s Gemma 4 26B A4B Instruct, 23.8 t/s

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 Just fits Q8_0 10.22 GB 11.8 t/s 16k
Gemma 4 E4B Instruct
Gemma 		8B Runs well Q8_0 8.39 GB 12.9 t/s 128k
Gemma 4 E2B Instruct
Gemma 		5.12B Runs well Q8_0 5.41 GB 20.3 t/s 128k
Qwen3 14B
Qwen 		14.77B Just fits Q4_K_M 9.97 GB 11.4 t/s 8k
Qwen3 8B
Qwen 		8.19B Runs well Q8_0 9.61 GB 12.1 t/s 8k
Qwen2.5 VL 7B Instruct
Qwen 		8.29B Runs well Q8_0 9 GB 12.8 t/s 32k
Qwen3.5 4B
Qwen 		4.66B Runs well Q8_0 5.24 GB 21.2 t/s 128k
Qwen2.5 7B Instruct
Qwen 		7.62B Runs well Q8_0 8.34 GB 14 t/s 32k
Gemma 3 12B Instruct
Gemma 		12.19B Just fits Q6_K 10.49 GB 10.3 t/s 8k
Qwen2.5 14B Instruct
Qwen 		14.77B Just fits Q4_K_M 10.22 GB 11.1 t/s 8k
Qwen2.5 Coder 14B Instruct
Qwen 		14.77B Just fits Q4_K_M 10.22 GB 11.1 t/s 8k
Granite 4.1 8B
Granite 		8.79B Just fits Q8_0 10.32 GB 10.5 t/s 8k
Qwen2.5 Coder 7B Instruct
Qwen 		7.62B Runs well Q8_0 8.34 GB 14 t/s 32k
Llama 3.1 8B Instruct
Llama 		8.03B Runs well Q8_0 9.32 GB 12.3 t/s 16k
Phi 4
Phi 		14.66B Just fits Q4_K_M 10.22 GB 10.9 t/s 8k
LFM2.5 8B A1B
Liquid 		8.47B (1.57B active) Runs great Q8_0 8.78 GB 36.6 t/s 64k
Qwen3 4B
Qwen 		4.02B Runs well Q8_0 5.43 GB 20.4 t/s 32k
Mistral 7B Instruct V0.3
Mistral 		7.25B Runs well Q8_0 8.55 GB 12.9 t/s 16k
Gemma 2 9B Instruct
Gemma 		9.24B Runs well Q6_K 9.39 GB 11.5 t/s 8k
Internlm3 8B Instruct
InternLM 		8.8B Runs well Q8_0 9.46 GB 12.1 t/s 32k
Gemma 3 4B Instruct
Gemma 		4.3B Runs well Q8_0 4.88 GB 22.9 t/s 128k
OLMo 3 7B Instruct
OLMo 		7.3B Just fits Q8_0 10.1 GB 11.2 t/s 8k
Mistral 7B Instruct V0.2
Mistral 		7.24B Runs well Q8_0 8.54 GB 12.9 t/s 16k
Phi 4 Mini Instruct
Phi 		3.84B Runs well Q8_0 5.14 GB 21.7 t/s 32k
Granite 4.1 3B
Granite 		3.4B Runs great Q8_0 4.31 GB 26.1 t/s 64k
Qwen2.5 3B Instruct
Qwen 		3.09B Runs great Q8_0 3.65 GB 31.2 t/s 32k
Phi 3 Mini 4k Instruct
Phi 		3.82B Runs well Q8_0 4.87 GB 23.5 t/s 4k
DeepSeek Coder 6.7B Instruct
DeepSeek 		6.74B Runs well Q6_K 9.52 GB 11.5 t/s 8k
Llama 3.2 3B Instruct
Llama 		3.21B Runs great Q8_0 4.39 GB 25.7 t/s 64k
LFM2.5 2.6B
Liquid 		2.7B Runs great Q8_0 3.11 GB 37.2 t/s 128k
Show the other 56 models
Qwen3.5 2B 2.27B Runs great Q8_0 2.67 GB 44.1 t/s 256k
Gemma 2 2B Instruct 2.61B Runs great Q8_0 3.51 GB 32.6 t/s 8k
Starcoder2 3B 3.03B Runs great Q8_0 3.46 GB 35.1 t/s 16k
Qwen3 1.7B 2.03B Runs great Q8_0 3.19 GB 36.1 t/s 32k
DeepSeek R1 Distill Qwen 1.5B 1.78B Runs great Q8_0 2.27 GB 59.5 t/s 128k
Qwen2.5 1.5B Instruct 1.54B Runs great Q8_0 2.03 GB 59.7 t/s 32k
SmolLM2 1.7B 1.71B Runs great Q8_0 3.5 GB 32.6 t/s 8k
OLMo 2 0425 1B 1.48B Runs great Q8_0 2.77 GB 46 t/s 4k
Llama 3.2 1B Instruct 1.24B Runs great Q8_0 1.79 GB 70.4 t/s 128k
LFM2.5 1.2B Instruct 1.17B Runs great Q8_0 1.56 GB 93 t/s 64k
Gemma 3 1B Instruct 1B Runs great Q8_0 1.32 GB 100.1 t/s 32k
Qwen3.5 0.8B 0.87B Runs great Q8_0 1.25 GB 106.9 t/s 256k
Qwen3 0.6B 0.75B Runs great Q8_0 1.89 GB 64.3 t/s 32k
Qwen2.5 0.5B Instruct 0.49B Runs great Q8_0 0.85 GB 179.8 t/s 32k
LFM2.5 350M 0.35B Runs great Q8_0 0.71 GB 278.4 t/s 64k
Qwen3.5 35B A3B 35.95B Fits only at 2 to 3 bits n/a 13.33 GB 48.9 t/s n/a
GLM 4.7 Flash 31.22B Fits only at 2 to 3 bits n/a 11.84 GB 35.4 t/s n/a
Qwen3 30B A3B 30.53B Fits only at 2 to 3 bits n/a 11.93 GB 31.3 t/s n/a
Qwen3 Coder 30B A3B Instruct 30.53B Fits only at 2 to 3 bits n/a 11.93 GB 31.3 t/s n/a
DeepSeek Coder V2 Lite Instruct 15.71B Just fits n/a 12.54 GB 26.2 t/s n/a
GPT OSS 20B 20.91B Just fits n/a 11.81 GB 25.3 t/s n/a
Phi 3.5 MoE Instruct 41.87B Fits only at 2 to 3 bits n/a 11.42 GB 23.3 t/s n/a
Gemma 4 26B A4B Instruct 25.81B Just fits n/a 13.93 GB 22.6 t/s n/a
Mixtral 8x7B Instruct V0.1 46.7B Fits only at 2 to 3 bits n/a 12.57 GB 14.8 t/s n/a
Mistral Nemo Instruct 2407 12.25B Just fits n/a 11.02 GB 10.3 t/s n/a
DeepSeek Coder 7B Instruct V1.5 6.91B Just fits n/a 10.96 GB 10.2 t/s n/a
Gemma 4 12B Instruct 11.96B Just fits n/a 10.81 GB 10 t/s n/a
Gemma 4 31B Instruct 31.27B Fits only at 2 to 3 bits n/a 11.2 GB 9.6 t/s n/a
Granite 4.1 30B 28.87B Fits only at 2 to 3 bits n/a 12.66 GB 8.5 t/s n/a
Mistral Small 24B Instruct 2501 23.57B Just fits n/a 13.32 GB 8.3 t/s n/a
Qwen3.5 27B 27.78B Just fits n/a 13.7 GB 8.2 t/s n/a
Qwen3 32B 32.76B Fits only at 2 to 3 bits n/a 14.08 GB 7.8 t/s n/a
Qwen2.5 32B Instruct 32.76B Fits only at 2 to 3 bits n/a 14.08 GB 7.8 t/s n/a
Qwen2.5 Coder 32B Instruct 32.76B Fits only at 2 to 3 bits n/a 14.08 GB 7.8 t/s n/a
Gemma 3 27B Instruct 27.43B Just fits n/a 13.99 GB 7.7 t/s n/a
Codestral 22B V0.1 22.25B Just fits n/a 14.7 GB 7.4 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

41 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.

DeviceMemoryBandwidthModels 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 M5 16GB

How much VRAM does an Apple M5 16GB have?

The Apple M5 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 M5 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 M5 16GB?

Qwen3.5 9B at Q8_0 is the strongest all-round fit: 10.22 GB used, around 11.8 tokens per second at 8k context.