Hardware / Apple /Apple M2 (10-core GPU)

Apple · Apple Silicon

Apple M2 (10-core GPU)

for example MacBook Air (2022), MacBook Pro 13-inch (2022), Mac mini (2023). Memory is a build option on these, so not every one of them is sold with 24 GB.

Runs 106 models fully in memory, 28 more with CPU offload. 6 of those sit close enough to 24 GB that our size estimate is what decides them.

Memory

24 GB

Bandwidth

100 GB/s

Runs

106

01

Specifications

Memory

24 GB

Decides which models fit at all.

Memory bandwidth

100 GB/s

How fast it can read the model. Sets the speed of the reply.

Compute

7.1 TFLOPS

Trillions of half-precision sums a second. Sets how fast it reads a long prompt, not how fast it replies.

Power draw

22 W

At full load, for sizing a power supply.

Released

Jun 24, 2022

Architecture

M2

02

What it runs

Best quant per model. Text models first, then speech, then what does not fit.

What is quantisation? →

ModelParamsContextSpeedVerdict

Llama 3.2 1B Instruct1.2B33K96 tok/sFits in memory Granite 4.0 Micro3.2B66K36 tok/sFits in memory Llama 3.2 3B Instruct3.2B131K36 tok/sFits in memory Ministral 3 3B 25123.8B131K30 tok/sFits in memory Gemma 3 4B4.3B131K27 tok/sFits in memory Nemotron 3.5 Content Safety4.3B66K27 tok/sFits in memory gpt-oss-safeguard-20b21.5B33K27 tok/sFits in memory Qwen3 8B8.2B66K14 tok/sFits in memory Llama 3.1 8B Instruct8B131K14 tok/sFits in memory Granite 4.1 8B8.8B66K13 tok/sFits in memory Qwen3.5-9B9.7B66K12 tok/sFits in memory Ministral 3 8B 25128.9B66K13 tok/sFits in memory Qwen3 VL 8B Thinking8.8B66K11 tok/sFits in memory UI-TARS 7B8.3B66K14 tok/sFits in memory Qwen3 VL 8B Instruct8.8B66K11 tok/sFits in memory Hy-MT2-1.8B2B8K49 tok/sFits in memory Granite 4.2 8B8.8B66K13 tok/sFits in memory Llama Guard 4 12B12B131K10 tok/sFits in memory Gemma 3 12B12.2B131K10 tok/sFits in memory Gemma 3n 4B7.8B33K15 tok/sFits in memory Qwen2.5 7B Instruct7.6B33K15 tok/sFits in memory Ministral 3 14B 251213.9B33K7 tok/sFits in memory Qwen3 14B14.8B33K7 tok/sFits in memory UnslopNemo 12B12.2B33K10 tok/sFits in memory Rocinante 12B12.2B33K10 tok/sFits in memory Mistral Nemo12.2B33K10 tok/sFits in memory Reka Edge7.1B16K16 tok/sFits in memory Phi 414.7B16K8 tok/sFits in memory Llama 3 8B Lunaris8B8K14 tok/sFits in memory Reka Flash 320.9B16K6 tok/sFits in memory Hy-MT2-7B8B8K11 tok/sFits in memory MythoMax 13B13B8K8 tok/sFits in memory Cydonia 24B V4.123.6B8K5 tok/sFits in memoryest Mistral Small 323.6B8K5 tok/sFits in memoryest ReMM SLERP 13B13B4K8 tok/sFits in memory Voxtral Small 24B 250724.3B4K5 tok/sFits in memoryest Uncensored24B4K5 tok/sFits in memoryest Mistral Small 3.2 24B24B4K5 tok/sFits in memoryest Mistral Small 3.1 24B24B4K5 tok/sFits in memoryest

Speech models it runs67 modelsTranscription and speech models that fit in memory. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.

Niagara 19m Batch.en20M5773 tok/sFits in memory Niagara 38m Batch.en38M1734 tok/sFits in memory Distil Large v3.50.8B123 tok/sFits in memory Hubert Large Ls960 ft0.3B308 tok/sFits in memory Wav2vec2 Large 960h Lv60 Self0.3B206 tok/sFits in memory Canary 180m Flash0.2B642 tok/sFits in memory Canary 1b Flash0.8B123 tok/sFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6B192 tok/sFits in memory Nemotron Speech Streaming en 0.6b0.6B192 tok/sFits in memory Parakeet CTC 0.6b0.6B192 tok/sFits in memory Parakeet RNNT 0.6b0.6B192 tok/sFits in memory Parakeet TDT CTC 110m0.1B1050 tok/sFits in memory Parakeet TDT 0.6b v20.6B192 tok/sFits in memory Parakeet TDT 0.6b v30.6B192 tok/sFits in memory Whisper Large v3 Turbo0.8B123 tok/sFits in memory MOSS Transcribe Diarize0.9B128 tok/sFits in memory Qwen3 ASR 0.6B0.9B128 tok/sFits in memory Qwen3 ASR 0.6B HF0.8B144 tok/sFits in memory Zipformer cr CTC Transducer XL 290M0.3B398 tok/sFits in memory Zipformer Transducer XL 290M0.3B398 tok/sFits in memory ASR Conformer Largescaleasr0.5B137 tok/sFits in memory Granite Speech 5.0 470m Turboctc0.5B231 tok/sFits in memory Granite Speech 5.0 470m Turboctc nc0.5B132 tok/sFits in memory Fun ASR Nano 2512 HF0.8B144 tok/sFits in memory Niagara 9m Batch.en9M7320 tok/sFits in memory Niagara 84m Batch.en84M784 tok/sFits in memory Owsm CTC v3.2 ft 1B1B116 tok/sFits in memory Owsm CTC v4 1B1B116 tok/sFits in memory MMS 1b All1B116 tok/sFits in memory Canary 1b1B116 tok/sFits in memory Canary 1b v21B116 tok/sFits in memory Audio8 ASR 0.1B0.3B33K385 tok/sFits in memory Owsm CTC v3.1 1B1.1B105 tok/sFits in memory Parakeet CTC 1.1b1.1B105 tok/sFits in memory Parakeet RNNT 1.1b1.1B105 tok/sFits in memory Parakeet TDT 1.1b1.1B105 tok/sFits in memory Lite Whisper Large v3 Acc1.4B83 tok/sFits in memory ARK ASR 0.6B1.3B33K89 tok/sFits in memory Whisper Large v31.5B77 tok/sFits in memory Nyra Health CrisperWhisper1.6B72 tok/sFits in memory Moonshine Streaming Medium0.3B4K220 tok/sFits in memory Moonshine Streaming Small0.1B4K1155 tok/sFits in memory Cohere Transcribe 03 20262.1B55 tok/sFits in memory Qwen3 ASR 1.7B HF2B58 tok/sFits in memory Granite 4.0 1b Speech2.3B50 tok/sFits in memory Granite Speech 4.1 2b2.3B50 tok/sFits in memory Granite Speech 4.1 2b NAR2.3B50 tok/sFits in memory Qwen3 ASR 1.7B2.3B50 tok/sFits in memory GLM ASR Nano 25122.3B50 tok/sFits in memory Higgs Audio v3 STT2.7B43 tok/sFits in memory STT 2.6b en2.6B44 tok/sFits in memory Canary Qwen 2.5b2.6B44 tok/sFits in memory Granite Speech 3.3 2b3B39 tok/sFits in memory MOSS Transcribe Preview 2B2.4B33K48 tok/sFits in memory Voxtral Mini 4B Realtime 26024.4B26 tok/sFits in memory Hojo ASR V15.2B22 tok/sFits in memory Voxtral Mini 3B 25074.7B25 tok/sFits in memory Gemma 4 E2B it5.1B23 tok/sFits in memory Phi 4 Multimodal Instruct5.6B66K21 tok/sFits in memory ARK ASR 3B4.1B33K28 tok/sFits in memory Gemma 4 E4B it8B131K14 tok/sFits in memory Higgs Audio v3 8b STT v28.9B11 tok/sFits in memory Granite Speech 3.3 8b8.6B13 tok/sFits in memory VibeVoice ASR HF8.3B12 tok/sFits in memory Gemma 4 12B it12B10 tok/sFits in memory Moonshine Streaming Tiny0B4Kno speed estimateFits in memory Moonshine Tiny0B194no speed estimateFits in memory

Runs only by spilling into system memory28 modelsThese load, but part of the weights sits in ordinary system memory, which is far slower than the chip.

Nex-N2-Mini35.1B—no speed estimateSpills to system RAM Qwen3.6 35B A3B36B—no speed estimateSpills to system RAMest Gemma 4 26B A4B25.8B—no speed estimateSpills to system RAMest Gemma 4 31B31.3B—no speed estimateSpills to system RAM Qwen3.5-27B27.8B—no speed estimateSpills to system RAMest GLM 4.7 Flash31.2B—no speed estimateSpills to system RAM Nemotron 3 Nano 30B A3B31.6B—no speed estimateSpills to system RAMest Olmo 3 32B Think32.2B—no speed estimateSpills to system RAM Qwen3 VL 32B Instruct33.4B—no speed estimateSpills to system RAM Qwen3 VL 30B A3B Thinking31.1B—no speed estimateSpills to system RAM Gemma 3 27B27.4B—no speed estimateSpills to system RAMest Skyfall 36B V236.9B—no speed estimateSpills to system RAMest Qwen2.5 Coder 32B Instruct32.8B—no speed estimateSpills to system RAM Laguna XS 2.133.4B—no speed estimateSpills to system RAMest Qwen3.6 27B27.8B—no speed estimateSpills to system RAM Qwen3.5-35B-A3B36B—no speed estimateSpills to system RAMest Qwen3 VL 30B A3B Instruct31.1B—no speed estimateSpills to system RAM Qwen3 30B A3B Thinking 250730.5B—no speed estimateSpills to system RAM Qwen3 Coder 30B A3B Instruct30.5B—no speed estimateSpills to system RAM Qwen3 30B A3B Instruct 250730.5B—no speed estimateSpills to system RAM Qwen3 32B32.8B—no speed estimateSpills to system RAM Gemma 2 27B27.2B—no speed estimateSpills to system RAM Muse Glimmer 30B29.8B—no speed estimateSpills to system RAM Nemotron 3.5 Lightning31.6B—no speed estimateSpills to system RAM Qwen3.8 27B27.8B—no speed estimateSpills to system RAM Hy-MT2-30B-A3B30.1B—no speed estimateSpills to system RAM Ternary Bonsai 2 27B27B—no speed estimateSpills to system RAM Nex-N2.5-Mini35.1B—no speed estimateSpills to system RAM

Too large for this device90 modelsThe weights do not fit even with part of them offloaded to system memory. Closest calls first.

Llama 3.3 Euryale 70B70.6B—no speed estimateToo large Qwen2.5 72B Instruct72.7B—no speed estimateToo large Qwen3 Coder Next79.7B—no speed estimateToo large GLM 4.5V108B—no speed estimateToo large Command A111B—no speed estimateToo large gpt-oss-120b120B—no speed estimateToo large Mistral Small 4119B—no speed estimateToo large Llama 3.1 70B Instruct70.6B—no speed estimateToo large Llama 3.3 70B Instruct70.6B—no speed estimateToo large Hermes 4 70B70.6B—no speed estimateToo large Llama 3.1 Euryale 70B v2.270.6B—no speed estimateToo large R1 Distill Llama 70B70.6B—no speed estimateToo large Hermes 3 70B Instruct70.6B—no speed estimateToo large Devstral 2 2512125B—no speed estimateToo large Ling-2.6-flash107B—no speed estimateToo large Magnum v4 72B72.7B—no speed estimateToo large Qwen2.5 VL 72B Instruct73.4B—no speed estimateToo large Laguna S 2.1118B—no speed estimateToo large Hunyuan A13B Instruct80.4B—no speed estimateToo large Mixtral 8x22B Instruct141B—no speed estimateToo large Qwen3 Next 80B A3B Thinking81.3B—no speed estimateToo large Qwen3 Next 80B A3B Instruct81.3B—no speed estimateToo large Nemotron 3 Super124B—no speed estimateToo large Mistral Medium 3.5128B—no speed estimateToo large Ling-3.0-flash128B—no speed estimateToo large GLM 4.6V108B—no speed estimateToo large Llama 4 Scout109B—no speed estimateToo large GLM 4.5 Air111B—no speed estimateToo large Step 3.7 Flash201B—no speed estimateToo large Qwen3.5-122B-A10B125B—no speed estimateToo large MiniMax M2229B—no speed estimateToo large Step 3.5 Flash199B—no speed estimateToo large Qwen3 VL 235B A22B Instruct236B—no speed estimateToo large MiniMax M2.7229B—no speed estimateToo large MiniMax M2.5229B—no speed estimateToo large Qwen3 235B A22B Instruct 2507235B—no speed estimateToo large Qwen3 VL 235B A22B Thinking236B—no speed estimateToo large DeepSeek V4 Flash291B—no speed estimateToo large DeepSeek V4 Flash Vision Exp305B—no speed estimateToo large Hy3299B—no speed estimateToo large GLM 5.3 Flash321B—no speed estimateToo large Laguna M.1226B—no speed estimateToo large MiniMax M2.1229B—no speed estimateToo large Qwen3 235B A22B Thinking 2507235B—no speed estimateToo large GLM 4.6357B—no speed estimateToo large GLM 4.7358B—no speed estimateToo large ERNIE 4.5 VL 424B A47B424B—no speed estimateToo large MiniMax M3427B—no speed estimateToo large Nex-N2.5-Pro397B—no speed estimateToo large Inkling Small266B—no speed estimateToo large Jamba Large 1.7399B—no speed estimateToo large Llama 4 Maverick402B—no speed estimateToo large Hermes 3 405B Instruct406B—no speed estimateToo large Qwen3 Coder 480B A35B480B—no speed estimateToo large Hy3 preview299B—no speed estimateToo large MiniMax-01456B—no speed estimateToo large MiMo-V2.5311B—no speed estimateToo large GLM 4.5358B—no speed estimateToo large DeepSeek V3.1685B—no speed estimateToo large Nex-N2-Pro397B—no speed estimateToo large Trinity Large Thinking399B—no speed estimateToo large Qwen3.5 397B A17B403B—no speed estimateToo large Hermes 4 405B406B—no speed estimateToo large GLM 5.1754B—no speed estimateToo large DeepSeek V4.1 Flash763B—no speed estimateToo large Hy4 preview780B—no speed estimateToo large MiniMax M1456B—no speed estimateToo large DeepSeek V3.1 Terminus685B—no speed estimateToo large DeepSeek V3685B—no speed estimateToo large GLM 5754B—no speed estimateToo large Inkling952B—no speed estimateToo large Nemotron 3 Ultra561B—no speed estimateToo large MiMo-V2.5-Pro1T—no speed estimateToo large Kimi K2 07111T—no speed estimateToo large Ling-2.6-1T1T—no speed estimateToo large Kimi K2.7 Code1.1T—no speed estimateToo large R1 0528685B—no speed estimateToo large DeepSeek V3 0324685B—no speed estimateToo large DeepSeek V3.2685B—no speed estimateToo large DeepSeek V3.2 Exp685B—no speed estimateToo large Kimi K2 09051T—no speed estimateToo large Ring-2.6-1T1T—no speed estimateToo large Kimi K2 Thinking1.1T—no speed estimateToo large Kimi K2.61.1T—no speed estimateToo large Kimi K2.51.1T—no speed estimateToo large GLM 5.2753B—no speed estimateToo large DeepSeek V4 Pro1.6T—no speed estimateToo large Qwen3.8 2.4T A95B2.4T—no speed estimateToo large LongCat 2.01.8T—no speed estimateToo large Kimi K32.8T—no speed estimateToo large

224 models have a verdict on this device: 106 fit in memory, 28 spill into system memory and 90 are too large. Every one of them is on this page.

03

Other M2 chips

The same generation in other memory sizes. Memory is what decides which models fit.

Apple M2 (8-core GPU, 8GB unified)8 GB · less memory Apple M2 Pro (19-core GPU)32 GB · more memory Apple M2 Max (38-core GPU)96 GB · more memory Apple M2 Ultra (76-core GPU)192 GB · more memory

Something wrong on this page? Tell us