Back to RunThisModel

Best AI Models for M1

16GB VRAM • apple • m1

VRAM
16GB Unified
Generation
m1
Vendor
apple
Runs Perfectly (S/A/B)
103
With Offloading (C/D)
5
Cannot Run (F)
1
S

Excellent (99 models)

Runs great with room for large context windows

Code Llama 13B Instruct

Meta

S
13BCodingQ4_K_M7.8GB

Gemma 3 12B

Google

S
12BChat / LLMQ4_K_M7.3GB

Mistral Nemo 12B

Mistral AI

S
12BChat / LLMQ4_K_M7.5GB

Solar 10.7B

Upstage

S
10.7BChat / LLMQ4_K_M6.5GB

Falcon 3 10B

TII

S
10BChat / LLMQ4_K_M6.4GB

Gemma 2 9B Instruct

Google

S
9.2BChat / LLMQ5_K_M6.7GB

Yi 1.5 9B Chat

01.AI

S
9BChat / LLMQ4_K_M5.5GB

Yi Coder 9B

01.AI

S
9BCodingQ4_K_M5.5GB

CodeGemma 7B

Google

S
8.5BCodingQ4_K_M5.5GB

DeepSeek R1 Distill 8B

DeepSeek

S
8BChat / LLMQ5_K_M5.8GB

Llama 3.1 8B Instruct

Meta

S
8BChat / LLMQ5_K_M5.8GB

Granite 3.3 8B

IBM

S
8BChat / LLMQ4_K_M5.1GB

EXAONE 3.5 7.8B

LG AI

S
7.8BChat / LLMQ4_K_M4.9GB

InternLM 2.5 7B

Shanghai AI Lab

S
7.7BChat / LLMQ4_K_M4.9GB

Qwen 2.5 7B Instruct

Alibaba

S
7.6BChat / LLMQ5_K_M6.2GB

Qwen 2.5 Coder 7B

Alibaba

S
7.6BCodingQ4_K_M4.9GB

Mistral 7B Instruct v0.3

Mistral AI

S
7.3BChat / LLMQ8_07.7GB

LLaVA 1.6 7B

LLaVA

S
7BMultimodalQ4_K_M5.0GB

Falcon 3 7B

TII

S
7BChat / LLMQ4_K_M5.0GB

OLMo 2 7B

Allen AI

S
7BChat / LLMQ8_07.7GB

OpenChat 3.5 7B

OpenChat

S
7BChat / LLMQ8_07.7GB

StarCoder2 7B

BigCode

S
7BCodingQ8_07.6GB

Code Llama 7B

Meta

S
7BCodingQ8_07.2GB

DeepSeek Coder 6.7B

DeepSeek

S
6.7BCodingQ8_07.2GB

Yi 1.5 6B Chat

01.AI

S
6BChat / LLMQ8_06.5GB

Phi-3.5 Vision

Microsoft

S
4.2BMultimodalQ4_K_M3.2GB

Gemma 3 4B

Google

S
4BChat / LLMQ8_04.3GB

Nemotron Mini 4B

NVIDIA

S
4BChat / LLMQ8_04.7GB

Danube 3 4B

H2O.ai

S
4BChat / LLMQ8_04.4GB

Phi-3.5 Mini 3.8B

Microsoft

S
3.8BChat / LLMQ8_04.3GB

Phi-4 Mini 3.8B

Microsoft

S
3.8BChat / LLMQ8_04.3GB

Stable Diffusion XL (CoreML)

Stability AI

S
3.5BImage GenerationCoreML3.3GB

SDXL Turbo (GGUF)

Stability AI

S
3.5BImage GenerationQ5_05.0GB

Llama 3.2 3B Instruct

Meta

S
3.2BChat / LLMQ8_03.7GB

Qwen 2.5 3B

Alibaba

S
3BChat / LLMQ8_03.9GB

Qwen 2.5 Coder 3B

Alibaba

S
3BCodingQ8_03.9GB

Falcon 3 3B

TII

S
3BChat / LLMQ8_03.8GB

StableLM Zephyr 3B

Stability AI

S
3BChat / LLMQ8_03.3GB

Rocket 3B

Pansophic

S
3BChat / LLMQ8_03.3GB

StarCoder2 3B

BigCode

S
3BCodingQ8_03.5GB

Stable Code 3B

Stability AI

S
3BCodingQ8_03.3GB

PaliGemma 3B

Google

S
3BMultimodalQ4_K_M2.5GB

Gemma 2 2B

Google

S
2.6BChat / LLMQ8_03.1GB

EXAONE 3.5 2.4B

LG AI

S
2.4BChat / LLMQ8_03.1GB

Qwen2-VL 2B

Alibaba

S
2.2BMultimodalQ8_02.0GB

CodeGemma 2B

Google

S
2BCodingQ8_03.0GB

MiniCPM-V 2.6

OpenBMB

S
2BMultimodalQ8_03.0GB

Granite 3.3 2B

IBM

S
2BChat / LLMQ8_03.0GB

Moondream 2

Moondream

S
1.8BMultimodalQ4_K_M1.5GB

SmolLM2 1.7B

HuggingFace

S
1.7BChat / LLMQ8_02.2GB

Whisper Large v3

OpenAI

S
1.55BSpeech RecognitionQ8_03.4GB

Qwen 2.5 1.5B

Alibaba

S
1.5BChat / LLMQ8_02.3GB

DeepSeek R1 Distill 1.5B

DeepSeek

S
1.5BChat / LLMQ8_02.3GB

Qwen 2.5 Coder 1.5B

Alibaba

S
1.5BCodingQ8_02.3GB

Yi Coder 1.5B

01.AI

S
1.5BCodingQ8_02.0GB

DeepSeek Coder 1.3B

DeepSeek

S
1.3BCodingQ8_01.8GB

Llama 3.2 1B Instruct

Meta

S
1.24BChat / LLMFP162.8GB

TinyLlama 1.1B

TinyLlama

S
1.1BChat / LLMQ8_01.6GB

Gemma 3 1B

Google

S
1BChat / LLMQ8_01.5GB

Falcon 3 1B

TII

S
1BChat / LLMQ8_02.2GB

Stable Diffusion 2.1 Base (CoreML)

Stability AI / Apple

S
0.86BImage GenerationCoreML-Palettized1.6GB

Stable Diffusion 1.5 (CoreML)

Runway

S
0.86BImage GenerationCoreML-Palettized2.5GB

Stable Diffusion 1.5 (GGUF)

Runway / GPUStack

S
0.86BImage GenerationQ8_02.3GB

Stable Diffusion 2.1 (GGUF)

Stability AI

S
0.86BImage GenerationQ8_02.7GB

Whisper Large v3 Turbo

OpenAI

S
0.81BSpeech RecognitionQ8_02.0GB

Whisper Medium

OpenAI

S
0.77BSpeech RecognitionQ8_01.9GB

Distil-Whisper Large v3

HuggingFace

S
0.76BSpeech RecognitionQ8_01.9GB

BGE Reranker v2 M3

BAAI

S
0.568BRerankerFP161.6GB

Qwen 2.5 0.5B

Alibaba

S
0.5BChat / LLMQ8_01.1GB

Qwen 2.5 Coder 0.5B

Alibaba

S
0.5BCodingQ8_01.1GB

Danube 3 500M

H2O.ai

S
0.5BChat / LLMQ8_01.0GB

SmolLM2 360M

HuggingFace

S
0.36BChat / LLMQ8_00.9GB

BGE Large EN v1.5

BAAI

S
0.335BEmbeddingFP161.1GB

MusicGen Small

Meta

S
0.3BAudio GenerationONNX-Q4F160.8GB

Whisper Small

OpenAI

S
0.24BSpeech RecognitionQ8_00.9GB

Nomic Embed Text v1.5

Nomic AI

S
0.137BEmbeddingFP160.8GB

SmolLM2 135M

HuggingFace

S
0.135BChat / LLMFP160.8GB

Kokoro 82M TTS

Kokoro

S
0.082BText to SpeechONNX-Q8F160.6GB

Whisper Base

OpenAI

S
0.074BSpeech RecognitionQ8_00.3GB

Whisper Base English

OpenAI

S
0.074BSpeech RecognitionQ8_00.3GB

Whisper Tiny English (Quantized)

OpenAI

S
0.039BSpeech RecognitionQ5_10.1GB

Whisper Tiny

OpenAI

S
0.039BSpeech RecognitionQ8_00.2GB

BGE Small EN v1.5

BAAI

S
0.033BEmbeddingQ8_00.1GB

Snowflake Arctic Embed S

Snowflake

S
0.033BEmbeddingQ8_00.1GB

Jina Reranker Tiny EN

Jina AI

S
0.033BRerankerFP160.1GB

all-MiniLM-L6-v2

Sentence Transformers

S
0.023BEmbeddingQ8_00.1GB

Piper TTS - Amy (English)

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - Lessac (English)

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - LibriTTS-R (English)

Rhasspy

S
0.02BText to SpeechONNX0.6GB

Piper TTS - Spanish (MLS)

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - French (Siwis)

Rhasspy

S
0.02BText to SpeechONNX0.5GB

Piper TTS - German (Thorsten)

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - Chinese (Huayan)

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - Japanese (Kokoro)

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - Korean

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - Russian (Irina)

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - Portuguese (Faber)

Rhasspy

S
0.02BText to SpeechONNX0.1GB

Piper TTS - Italian (Riccardo)

Rhasspy

S
0.02BText to SpeechONNX0.5GB

Piper TTS - Arabic (Kareem)

Rhasspy

S
0.02BText to SpeechONNX0.1GB
A

Great (4 models)

Runs well with good performance

Phi-4

Microsoft

A
14BChat / LLMQ4_K_M8.9GB

Qwen 2.5 14B

Alibaba

A
14BChat / LLMQ4_K_M8.9GB

Qwen 2.5 Coder 14B

Alibaba

A
14BCodingQ4_K_M8.9GB

Stable Diffusion 3 Medium (GGUF)

Stability AI

A
2.5BImage GenerationQ8_09.2GB
C

Possible (3 models)

Needs partial CPU offloading, slower performance

Mistral Small 22B

Mistral AI

C
22BChat / LLMQ4_K_M12.9GB

FLUX.1 Schnell (GGUF)

Black Forest Labs

C
12BImage GenerationQ5_014.0GB

FLUX.1 Dev (GGUF)

Black Forest Labs

C
12BImage GenerationQ5_014.0GB
D

Struggling (2 models)

Heavy offloading required, very slow

Qwen 2.5 32B

Alibaba

D
32BChat / LLMQ4_K_M19.0GB

Gemma 3 27B

Google

D
27BChat / LLMQ4_K_M15.9GB
F

Cannot Run (1 model)

Insufficient hardware to run this model

Llama 3.1 70B Instruct

Meta

F
70BChat / LLMFP16142.0GB

Similar GPUs

AMD Radeon RX 6800

16GB$579amd

AMD Radeon RX 6800 XT

16GB$649amd

AMD Radeon RX 6900 XT

16GB$999amd

AMD Radeon RX 6950 XT

16GB$1,099amd

AMD Radeon RX 7600 XT

16GB$329amd

AMD Radeon RX 7800 XT

16GB$499amd

AMD Radeon RX 7900 GRE

16GB$549amd

AMD Radeon RX 9070

16GB$449amd

AMD Radeon RX 9070 XT

16GB$549amd

Intel Arc A770

16GB$349intel

NVIDIA GeForce RTX 4060 Ti 16GB

16GB$499nvidia

NVIDIA GeForce RTX 4070 Ti SUPER

16GB$799nvidia

Frequently Asked Questions

What AI models can I run on the Apple M1?
The Apple M1 with 16GB VRAM can run 103 AI models smoothly (grade B or better), including Code Llama 13B Instruct, Gemma 3 12B, Mistral Nemo 12B and 100 more.
How much VRAM does the Apple M1 have?
The Apple M1 has 16GB of VRAM (unified memory), which is sufficient for running many local AI models.
Is the Apple M1 good for AI?
With 16GB VRAM, the Apple M1 can run 103 out of 109 models in our database at grade B or better. This provides good capability for many popular models.