Hardware / Apple /Apple M2 Pro (19-core GPU)

Apple · Apple Silicon

Apple M2 Pro (19-core GPU)

for example MacBook Pro 14-inch and 16-inch (2023), Mac mini (2023). Memory is a build option on these, so not every one of them is sold with 32 GB.

Runs 129 models fully in memory, 5 more with CPU offload. 6 of those sit close enough to 32 GB that our size estimate is what decides them.

Memory

32 GB

Bandwidth

200 GB/s

Runs

129

01

Specifications

Memory

32 GB

Decides which models fit at all.

Memory bandwidth

200 GB/s

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

Compute

13.6 TFLOPS

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

Power draw

35 W

At full load, for sizing a power supply.

Released

Jan 24, 2023

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 Instruct1.2B33K192 tok/sFits in memory Granite 4.0 Micro3.2B66K72 tok/sFits in memory Llama 3.2 3B Instruct3.2B131K72 tok/sFits in memory Hy-MT2-1.8B2B8K98 tok/sFits in memory Ministral 3 3B 25123.8B131K61 tok/sFits in memory gpt-oss-safeguard-20b21.5B131K55 tok/sFits in memory Nemotron 3 Nano 30B A3B31.6B33K65 tok/sFits in memory Gemma 3 4B4.3B131K54 tok/sFits in memory Nemotron 3.5 Content Safety4.3B131K54 tok/sFits in memory Qwen3 VL 30B A3B Thinking31.1B16K65 tok/sFits in memory Qwen3 VL 30B A3B Instruct31.1B16K65 tok/sFits in memory Qwen3 30B A3B Thinking 250730.5B16K65 tok/sFits in memory Qwen3 Coder 30B A3B Instruct30.5B16K65 tok/sFits in memory Qwen3 30B A3B Instruct 250730.5B16K65 tok/sFits in memory Granite 4.1 8B8.8B66K26 tok/sFits in memory Qwen3 VL 8B Thinking8.8B66K26 tok/sFits in memory UI-TARS 7B8.3B66K28 tok/sFits in memory Qwen3 VL 8B Instruct8.8B66K26 tok/sFits in memory Qwen3 8B8.2B66K28 tok/sFits in memory Llama 3.1 8B Instruct8B131K29 tok/sFits in memory Hy-MT2-30B-A3B30.1B8K65 tok/sFits in memory Granite 4.2 8B8.8B66K26 tok/sFits in memory Gemma 4 26B A4B25.8B16K49 tok/sFits in memory Qwen3.5-9B9.7B66K24 tok/sFits in memory Ministral 3 8B 25128.9B66K26 tok/sFits in memory Llama Guard 4 12B12B131K19 tok/sFits in memory Gemma 3 12B12.2B131K19 tok/sFits in memory Rocinante 12B12.2B66K19 tok/sFits in memory Mistral Nemo12.2B66K19 tok/sFits in memory Qwen2.5 7B Instruct7.6B33K30 tok/sFits in memory Ministral 3 14B 251213.9B66K17 tok/sFits in memory Gemma 3n 4B7.8B33K30 tok/sFits in memory Qwen3 14B14.8B66K16 tok/sFits in memory Reka Flash 320.9B66K11 tok/sFits in memory Reka Edge7.1B16K33 tok/sFits in memory UnslopNemo 12B12.2B33K19 tok/sFits in memory Cydonia 24B V4.123.6B33K10 tok/sFits in memory Uncensored24B33K10 tok/sFits in memory Mistral Small 3.2 24B24B33K10 tok/sFits in memory Gemma 3 27B27.4B33K8 tok/sFits in memory Mistral Small 3.1 24B24B33K10 tok/sFits in memory Mistral Small 323.6B33K10 tok/sFits in memory Muse Glimmer 30B29.8B33K8 tok/sFits in memory Nemotron 3.5 Lightning31.6B33K6 tok/sFits in memory Ternary Bonsai 2 27B27B33K9 tok/sFits in memory Phi 414.7B16K16 tok/sFits in memory Llama 3 8B Lunaris8B8K29 tok/sFits in memory Hy-MT2-7B8B8K25 tok/sFits in memory Qwen3.5-27B27.8B16K8 tok/sFits in memory Voxtral Small 24B 250724.3B16K10 tok/sFits in memory Qwen3.6 27B27.8B16K8 tok/sFits in memory Qwen3.8 27B27.8B16K8 tok/sFits in memory MythoMax 13B13B8K15 tok/sFits in memory GLM 4.7 Flash31.2B8K6 tok/sFits in memory Gemma 2 27B27.2B8K7 tok/sFits in memoryest ReMM SLERP 13B13B4K15 tok/sFits in memory Laguna XS 2.133.4B8K6 tok/sFits in memory Olmo 3 32B Think32.2B4K7 tok/sFits in memoryest Qwen3 VL 32B Instruct33.4B4K7 tok/sFits in memoryest Qwen2.5 Coder 32B Instruct32.8B4K7 tok/sFits in memoryest Qwen3 32B32.8B4K7 tok/sFits in memoryest Gemma 4 31B31.3B2K7 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.en20M11546 tok/sFits in memory Niagara 38m Batch.en38M5180 tok/sFits in memory Distil Large v3.50.8B246 tok/sFits in memory Lite Whisper Large v3 Acc1.4B141 tok/sFits in memory Owsm CTC v3.1 1B1.1B210 tok/sFits in memory Owsm CTC v3.2 ft 1B1B231 tok/sFits in memory Owsm CTC v4 1B1B197 tok/sFits in memory Hubert Large Ls960 ft0.3B615 tok/sFits in memory MMS 1b All1B132 tok/sFits in memory Wav2vec2 Large 960h Lv60 Self0.3B412 tok/sFits in memory Canary 180m Flash0.2B1283 tok/sFits in memory Canary 1b1B132 tok/sFits in memory Canary 1b Flash0.8B165 tok/sFits in memory Canary 1b v21B132 tok/sFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6B220 tok/sFits in memory Nemotron Speech Streaming en 0.6b0.6B220 tok/sFits in memory Parakeet CTC 0.6b0.6B385 tok/sFits in memory Parakeet CTC 1.1b1.1B120 tok/sFits in memory Parakeet RNNT 0.6b0.6B220 tok/sFits in memory Parakeet RNNT 1.1b1.1B210 tok/sFits in memory Parakeet TDT CTC 110m0.1B1198 tok/sFits in memory Parakeet TDT 0.6b v20.6B328 tok/sFits in memory Parakeet TDT 0.6b v30.6B385 tok/sFits in memory Parakeet TDT 1.1b1.1B120 tok/sFits in memory Nyra Health CrisperWhisper1.6B144 tok/sFits in memory Whisper Large v31.5B131 tok/sFits in memory Whisper Large v3 Turbo0.8B246 tok/sFits in memory MOSS Transcribe Diarize0.9B146 tok/sFits in memory Qwen3 ASR 0.6B0.9B257 tok/sFits in memory Qwen3 ASR 0.6B HF0.8B289 tok/sFits in memory Zipformer cr CTC Transducer XL 290M0.3B679 tok/sFits in memory Zipformer Transducer XL 290M0.3B454 tok/sFits in memory ASR Conformer Largescaleasr0.5B481 tok/sFits in memory Granite Speech 5.0 470m Turboctc0.5B394 tok/sFits in memory Granite Speech 5.0 470m Turboctc nc0.5B264 tok/sFits in memory Fun ASR Nano 2512 HF0.8B289 tok/sFits in memory Niagara 9m Batch.en9M14641 tok/sFits in memory Niagara 84m Batch.en84M1569 tok/sFits in memory Qwen3 ASR 1.7B HF2B116 tok/sFits in memory Cohere Transcribe 03 20262.1B110 tok/sFits in memory ARK ASR 0.6B1.3B33K178 tok/sFits in memory Audio8 ASR 0.1B0.3B33K770 tok/sFits in memory Granite 4.0 1b Speech2.3B100 tok/sFits in memory Granite Speech 4.1 2b2.3B100 tok/sFits in memory Granite Speech 4.1 2b NAR2.3B100 tok/sFits in memory Qwen3 ASR 1.7B2.3B100 tok/sFits in memory GLM ASR Nano 25122.3B100 tok/sFits in memory STT 2.6b en2.6B89 tok/sFits in memory Canary Qwen 2.5b2.6B89 tok/sFits in memory Higgs Audio v3 STT2.7B86 tok/sFits in memory MOSS Transcribe Preview 2B2.4B33K96 tok/sFits in memory Granite Speech 3.3 2b3B77 tok/sFits in memory Moonshine Streaming Medium0.3B4K770 tok/sFits in memory Moonshine Streaming Small0.1B4K1318 tok/sFits in memory Voxtral Mini 4B Realtime 26024.4B53 tok/sFits in memory Voxtral Mini 3B 25074.7B49 tok/sFits in memory ARK ASR 3B4.1B33K56 tok/sFits in memory Hojo ASR V15.2B45 tok/sFits in memory Gemma 4 E2B it5.1B45 tok/sFits in memory Phi 4 Multimodal Instruct5.6B131K41 tok/sFits in memory Granite Speech 3.3 8b8.6B27 tok/sFits in memory VibeVoice ASR HF8.3B28 tok/sFits in memory Gemma 4 E4B it8B131K29 tok/sFits in memory Higgs Audio v3 8b STT v28.9B26 tok/sFits in memory Gemma 4 12B it12B19 tok/sFits in memory Moonshine Streaming Tiny0B4Kno speed estimateFits in memory Moonshine Tiny0B194no speed estimateFits in memory

Runs only by spilling into system memory5 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 RAMest Qwen3.6 35B A3B36B—no speed estimateSpills to system RAMest Skyfall 36B V236.9B—no speed estimateSpills to system RAMest Qwen3.5-35B-A3B36B—no speed estimateSpills to system RAMest 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 70B Instruct70.6B—no speed estimateToo large Llama 3.3 Euryale 70B70.6B—no speed estimateToo large Qwen3 Next 80B A3B Thinking81.3B—no speed estimateToo large GLM 4.6V108B—no speed estimateToo large GLM 4.5V108B—no speed estimateToo large Command A111B—no speed estimateToo large gpt-oss-120b120B—no speed estimateToo large Llama 3.1 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 72B Instruct72.7B—no speed estimateToo large Mistral Medium 3.5128B—no speed estimateToo large Qwen2.5 VL 72B Instruct73.4B—no speed estimateToo large Qwen3 Coder Next79.7B—no speed estimateToo large Laguna S 2.1118B—no speed estimateToo large Hunyuan A13B Instruct80.4B—no speed estimateToo large Qwen3 Next 80B A3B Instruct81.3B—no speed estimateToo large Nemotron 3 Super124B—no speed estimateToo large Mixtral 8x22B Instruct141B—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 Mistral Small 4119B—no speed estimateToo large Qwen3.5-122B-A10B125B—no speed estimateToo large Ling-3.0-flash128B—no speed estimateToo large Step 3.5 Flash199B—no speed estimateToo large Qwen3 VL 235B A22B Thinking236B—no speed estimateToo large Qwen3 VL 235B A22B Instruct236B—no speed estimateToo large Inkling Small266B—no speed estimateToo large MiniMax M2.7229B—no speed estimateToo large MiniMax M2.5229B—no speed estimateToo large MiniMax M2229B—no speed estimateToo large Qwen3 235B A22B Instruct 2507235B—no speed estimateToo large DeepSeek V4 Flash291B—no speed estimateToo large GLM 5.3 Flash321B—no speed estimateToo large Hy3299B—no speed estimateToo large Laguna M.1226B—no speed estimateToo large Nex-N2-Pro397B—no speed estimateToo large Trinity Large Thinking399B—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 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 DeepSeek V4 Flash Vision Exp305B—no speed estimateToo large MiniMax-01456B—no speed estimateToo large MiMo-V2.5311B—no speed estimateToo large GLM 4.5358B—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 MiniMax M1456B—no speed estimateToo large DeepSeek V3.1 Terminus685B—no speed estimateToo large DeepSeek V3685B—no speed estimateToo large DeepSeek V3.2685B—no speed estimateToo large GLM 5754B—no speed estimateToo large DeepSeek V4.1 Flash763B—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 V3.1685B—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 K2.61.1T—no speed estimateToo large Kimi K2.51.1T—no speed estimateToo large GLM 5.2753B—no speed estimateToo large Hy4 preview780B—no speed estimateToo large Kimi K2 Thinking1.1T—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: 129 fit in memory, 5 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 (10-core GPU)24 GB · less 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