Hardware / Apple /Apple M1 Max (32-core GPU)

Apple · Apple Silicon

Apple M1 Max (32-core GPU)

for example MacBook Pro 14-inch and 16-inch (2021), Mac Studio (2022). Memory is a build option on these, so not every one of them is sold with 64 GB.

Runs 141 models fully in memory, 10 more with CPU offload. 7 of those sit close enough to 64 GB that our size estimate is what decides them.

Memory

64 GB

Bandwidth

400 GB/s

Runs

141

01

Specifications

Memory

64 GB

Decides which models fit at all.

Memory bandwidth

400 GB/s

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

Compute

21.2 TFLOPS

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

Power draw

60 W

At full load, for sizing a power supply.

Released

Oct 26, 2021

Architecture

M1

02

What it runs

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

What is quantisation? →

ModelParamsContextSpeedVerdict

Qwen3.6 35B A3B36B262K131 tok/sFits in memory Nemotron 3 Nano 30B A3B31.6B262K131 tok/sFits in memory Ministral 3 3B 25123.8B131K122 tok/sFits in memory Granite 4.0 Micro3.2B66K123 tok/sFits in memory Qwen3 VL 30B A3B Thinking31.1B262K131 tok/sFits in memory Llama 3.2 3B Instruct3.2B131K144 tok/sFits in memory Qwen3.5-35B-A3B36B262K131 tok/sFits in memory Qwen3 VL 30B A3B Instruct31.1B262K131 tok/sFits in memory Qwen3 30B A3B Thinking 250730.5B66K131 tok/sFits in memory Qwen3 Coder 30B A3B Instruct30.5B262K131 tok/sFits in memory Qwen3 30B A3B Instruct 250730.5B262K131 tok/sFits in memory gpt-oss-safeguard-20b21.5B131K109 tok/sFits in memory Llama 3.2 1B Instruct1.2B33K220 tok/sFits in memory Gemma 3 4B4.3B131K107 tok/sFits in memory Nemotron 3.5 Content Safety4.3B131K107 tok/sFits in memory Gemma 4 26B A4B25.8B66K98 tok/sFits in memory Hy-MT2-1.8B2B8K196 tok/sFits in memory Hy-MT2-30B-A3B30.1B8K131 tok/sFits in memory UI-TARS 7B8.3B66K56 tok/sFits in memory Qwen3 8B8.2B131K56 tok/sFits in memory Llama 3.1 8B Instruct8B131K58 tok/sFits in memory Granite 4.1 8B8.8B131K53 tok/sFits in memory Ministral 3 8B 25128.9B262K52 tok/sFits in memory Qwen3 VL 8B Thinking8.8B131K53 tok/sFits in memory Qwen3 VL 8B Instruct8.8B262K53 tok/sFits in memory Granite 4.2 8B8.8B131K53 tok/sFits in memory Qwen3.5-9B9.7B262K48 tok/sFits in memory Gemma 3n 4B7.8B33K59 tok/sFits in memory Qwen2.5 7B Instruct7.6B33K61 tok/sFits in memory Reka Edge7.1B16K65 tok/sFits in memory Llama Guard 4 12B12B262K39 tok/sFits in memory Gemma 3 12B12.2B131K38 tok/sFits in memory Rocinante 12B12.2B66K38 tok/sFits in memory Mistral Nemo12.2B131K38 tok/sFits in memory Ministral 3 14B 251213.9B131K33 tok/sFits in memory Qwen3 14B14.8B131K31 tok/sFits in memory UnslopNemo 12B12.2B33K38 tok/sFits in memory Reka Flash 320.9B66K22 tok/sFits in memory Cydonia 24B V4.123.6B131K20 tok/sFits in memory Uncensored24B66K19 tok/sFits in memory Mistral Small 3.2 24B24B131K19 tok/sFits in memory Llama 3 8B Lunaris8B8K58 tok/sFits in memory Mistral Small 3.1 24B24B66K19 tok/sFits in memory Qwen3.5-27B27.8B66K17 tok/sFits in memory Olmo 3 32B Think32.2B66K14 tok/sFits in memory Gemma 3 27B27.4B262K17 tok/sFits in memory Qwen3.6 27B27.8B66K14 tok/sFits in memory Qwen3 32B32.8B66K14 tok/sFits in memory Muse Glimmer 30B29.8B131K16 tok/sFits in memory Qwen3.8 27B27.8B66K14 tok/sFits in memory Ternary Bonsai 2 27B27B262K15 tok/sFits in memory Nex-N2-Mini35.1B262K11 tok/sFits in memory GLM 4.7 Flash31.2B66K13 tok/sFits in memory Qwen3 VL 32B Instruct33.4B66K12 tok/sFits in memory Laguna XS 2.133.4B66K10 tok/sFits in memory Nemotron 3.5 Lightning31.6B262K11 tok/sFits in memory Hy-MT2-7B8B8K49 tok/sFits in memory Nex-N2.5-Mini35.1B262K11 tok/sFits in memory Phi 414.7B16K31 tok/sFits in memory Mistral Small 323.6B33K20 tok/sFits in memory Qwen2.5 Coder 32B Instruct32.8B33K14 tok/sFits in memory Skyfall 36B V236.9B33K13 tok/sFits in memory MythoMax 13B13B8K36 tok/sFits in memory Voxtral Small 24B 250724.3B16K19 tok/sFits in memory Gemma 4 31B31.3B16K15 tok/sFits in memory ReMM SLERP 13B13B4K36 tok/sFits in memory Gemma 2 27B27.2B8K17 tok/sFits in memory Llama 3.1 70B Instruct70.6B4K7 tok/sFits in memoryest Llama 3.3 70B Instruct70.6B4K7 tok/sFits in memoryest Hermes 4 70B70.6B2K7 tok/sFits in memoryest Llama 3.3 Euryale 70B70.6B2K7 tok/sFits in memoryest Llama 3.1 Euryale 70B v2.270.6B2K7 tok/sFits in memoryest R1 Distill Llama 70B70.6B2K7 tok/sFits in memoryest Hermes 3 70B Instruct70.6B2K7 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.en20M13177 tok/sFits in memory Niagara 38m Batch.en38M6935 tok/sFits in memory Higgs Audio v3 STT2.7B146 tok/sFits in memory Cohere Transcribe 03 20262.1B126 tok/sFits in memory Distil Large v3.50.8B329 tok/sFits in memory Lite Whisper Large v3 Acc1.4B281 tok/sFits in memory Owsm CTC v3.1 1B1.1B420 tok/sFits in memory Owsm CTC v3.2 ft 1B1B264 tok/sFits in memory Owsm CTC v4 1B1B462 tok/sFits in memory Hubert Large Ls960 ft0.3B824 tok/sFits in memory MMS 1b All1B394 tok/sFits in memory Wav2vec2 Large 960h Lv60 Self0.3B824 tok/sFits in memory Granite 4.0 1b Speech2.3B201 tok/sFits in memory Granite Speech 3.3 2b3B154 tok/sFits in memory Granite Speech 4.1 2b2.3B201 tok/sFits in memory Granite Speech 4.1 2b NAR2.3B171 tok/sFits in memory STT 2.6b en2.6B178 tok/sFits in memory Canary 180m Flash0.2B2187 tok/sFits in memory Canary 1b1B462 tok/sFits in memory Canary 1b Flash0.8B329 tok/sFits in memory Canary 1b v21B264 tok/sFits in memory Canary Qwen 2.5b2.6B178 tok/sFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6B439 tok/sFits in memory Nemotron Speech Streaming en 0.6b0.6B439 tok/sFits in memory Parakeet CTC 0.6b0.6B770 tok/sFits in memory Parakeet CTC 1.1b1.1B240 tok/sFits in memory Parakeet RNNT 0.6b0.6B439 tok/sFits in memory Parakeet RNNT 1.1b1.1B420 tok/sFits in memory Parakeet TDT CTC 110m0.1B2396 tok/sFits in memory Parakeet TDT 0.6b v20.6B656 tok/sFits in memory Parakeet TDT 0.6b v30.6B439 tok/sFits in memory Parakeet TDT 1.1b1.1B240 tok/sFits in memory Nyra Health CrisperWhisper1.6B165 tok/sFits in memory Whisper Large v31.5B262 tok/sFits in memory Whisper Large v3 Turbo0.8B577 tok/sFits in memory MOSS Transcribe Diarize0.9B293 tok/sFits in memory Qwen3 ASR 0.6B0.9B513 tok/sFits in memory Qwen3 ASR 0.6B HF0.8B577 tok/sFits in memory Qwen3 ASR 1.7B2.3B171 tok/sFits in memory Qwen3 ASR 1.7B HF2B132 tok/sFits in memory Zipformer cr CTC Transducer XL 290M0.3B1358 tok/sFits in memory Zipformer Transducer XL 290M0.3B909 tok/sFits in memory ASR Conformer Largescaleasr0.5B962 tok/sFits in memory GLM ASR Nano 25122.3B171 tok/sFits in memory Granite Speech 5.0 470m Turboctc0.5B787 tok/sFits in memory Granite Speech 5.0 470m Turboctc nc0.5B527 tok/sFits in memory Fun ASR Nano 2512 HF0.8B577 tok/sFits in memory Niagara 9m Batch.en9M43742 tok/sFits in memory Niagara 84m Batch.en84M3137 tok/sFits in memory ARK ASR 0.6B1.3B33K203 tok/sFits in memory Audio8 ASR 0.1B0.3B33K878 tok/sFits in memory MOSS Transcribe Preview 2B2.4B33K192 tok/sFits in memory Voxtral Mini 4B Realtime 26024.4B105 tok/sFits in memory ARK ASR 3B4.1B33K113 tok/sFits in memory Voxtral Mini 3B 25074.7B98 tok/sFits in memory Gemma 4 E2B it5.1B91 tok/sFits in memory Hojo ASR V15.2B89 tok/sFits in memory Phi 4 Multimodal Instruct5.6B131K83 tok/sFits in memory Moonshine Streaming Medium0.3B4K1540 tok/sFits in memory Moonshine Streaming Small0.1B4K2635 tok/sFits in memory VibeVoice ASR HF8.3B56 tok/sFits in memory Gemma 4 E4B it8B131K58 tok/sFits in memory Higgs Audio v3 8b STT v28.9B52 tok/sFits in memory Granite Speech 3.3 8b8.6B54 tok/sFits in memory Gemma 4 12B it12B39 tok/sFits in memory Moonshine Streaming Tiny0B4Kno speed estimateFits in memory Moonshine Tiny0B194no speed estimateFits in memory

Runs only by spilling into system memory10 modelsThese load, but part of the weights sits in ordinary system memory, which is far slower than the chip.

Ling-2.6-flash107B—no speed estimateSpills to system RAMest Qwen3 Coder Next79.7B—no speed estimateSpills to system RAM GLM 4.6V108B—no speed estimateSpills to system RAMest Qwen3 Next 80B A3B Thinking81.3B—no speed estimateSpills to system RAM Hunyuan A13B Instruct80.4B—no speed estimateSpills to system RAM Qwen2.5 VL 72B Instruct73.4B—no speed estimateSpills to system RAM Magnum v4 72B72.7B—no speed estimateSpills to system RAMest Qwen3 Next 80B A3B Instruct81.3B—no speed estimateSpills to system RAM GLM 4.5V108B—no speed estimateSpills to system RAMest Qwen2.5 72B Instruct72.7B—no speed estimateSpills to system RAMest

Too large for this device73 modelsThe weights do not fit even with part of them offloaded to system memory. Closest calls first.

GLM 4.5 Air111B—no speed estimateToo largeest Nemotron 3 Super124B—no speed estimateToo large Qwen3.5-122B-A10B125B—no speed estimateToo large Command A111B—no speed estimateToo large Mistral Small 4119B—no speed estimateToo large Devstral 2 2512125B—no speed estimateToo large Mistral Medium 3.5128B—no speed estimateToo large Laguna S 2.1118B—no speed estimateToo large Mixtral 8x22B Instruct141B—no speed estimateToo large Llama 4 Scout109B—no speed estimateToo large gpt-oss-120b120B—no speed estimateToo large Ling-3.0-flash128B—no speed estimateToo large MiniMax M2.7229B—no speed estimateToo large Step 3.5 Flash199B—no speed estimateToo large Qwen3 VL 235B A22B Instruct236B—no speed estimateToo large Step 3.7 Flash201B—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 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 MiniMax M2229B—no speed estimateToo large Hermes 4 405B406B—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 MiniMax-01456B—no speed estimateToo large Nex-N2.5-Pro397B—no speed estimateToo large Inkling Small266B—no speed estimateToo large Trinity Large Thinking399B—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 ERNIE 4.5 VL 424B A47B424B—no speed estimateToo large MiniMax M3427B—no speed estimateToo large Hy3 preview299B—no speed estimateToo large DeepSeek V4 Flash Vision Exp305B—no speed estimateToo large MiMo-V2.5311B—no speed estimateToo large Nemotron 3 Ultra561B—no speed estimateToo large GLM 4.5358B—no speed estimateToo large Nex-N2-Pro397B—no speed estimateToo large Jamba Large 1.7399B—no speed estimateToo large Qwen3.5 397B A17B403B—no speed estimateToo large GLM 5.1754B—no speed estimateToo large GLM 5.2753B—no speed estimateToo large MiniMax M1456B—no speed estimateToo large R1 0528685B—no speed estimateToo large DeepSeek V3.1 Terminus685B—no speed estimateToo large DeepSeek V3685B—no speed estimateToo large DeepSeek V3.1685B—no speed estimateToo large GLM 5754B—no speed estimateToo large DeepSeek V4.1 Flash763B—no speed estimateToo large Inkling952B—no speed estimateToo large Kimi K2 07111T—no speed estimateToo large Ling-2.6-1T1T—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 K2.61.1T—no speed estimateToo large Kimi K2.51.1T—no speed estimateToo large Hy4 preview780B—no speed estimateToo large DeepSeek V4 Pro1.6T—no speed estimateToo large LongCat 2.01.8T—no speed estimateToo large MiMo-V2.5-Pro1T—no speed estimateToo large Kimi K2 Thinking1.1T—no speed estimateToo large Kimi K2.7 Code1.1T—no speed estimateToo large Qwen3.8 2.4T A95B2.4T—no speed estimateToo large Kimi K32.8T—no speed estimateToo large

224 models have a verdict on this device: 141 fit in memory, 10 spill into system memory and 73 are too large. Every one of them is on this page.

03

Other M1 chips

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

Apple M1 (8-core GPU, 8GB unified)8 GB · less memory Apple M1 (8-core GPU)16 GB · less memory Apple M1 Pro (16-core GPU)32 GB · less memory Apple M1 Ultra (64-core GPU)128 GB · more memory

Something wrong on this page? Tell us